Differences

This shows you the differences between two versions of the page.

--- brainstorming:index [2021/04/07 15:05]
nbuisard
+++ brainstorming:index [2024/06/07 16:51] (current)
ahuaulme
@@ Line 1: / Line 1: @@
 <html><div class="pageTitle"> Les partages de midi </div><br></html>
-~~NOTOC~~
-{{:brainstorming:img_20200922_1324191-panorama.jpg?300|}}
-{{:brainstorming:capture_d_e_cran_2020-03-31_a_15.13.50_-_copie.png?230|}}
 ====== Présentation ======
 ===== Qu'est-ce que c'est ? =====
@@ Line 16: / Line 15: @@
   * Afin que nous soyons le plus nombreux possible aux partages de midi, merci d'informer le/la coordinat-[eur/rice] de vos absences.
+{{:brainstorming:img_20200922_1324191-panorama.jpg?300|}}
+{{:brainstorming:capture_d_e_cran_2020-03-31_a_15.13.50_-_copie.png?230|}}
 ===== Coordination =====
-  * [[:members:julien.berthelemy:index| Julien Berthelemy]]
+  * [[:members:john.baxter:index| John Baxter]]
+  * [[:members:arnaud.huaulme:index| Arnaud Huaulmé]]
+  * [[:members:noemie.buisard:index| Noémie Buisard]]
 ====== Agenda ======
-===== Mardi 06 avril 2021 13:00-14:00 =====
+===== 2024 =====
+**June 13, 2024 : Not without the students. A history of image-guided surgery in the NIST lab in the Montreal Neurological Institute** \\
+  * **Speaker:** Pr. Louis Collins de l’Université de Mc Gill de Montréal\\
+  * **Sumarry:** This talk will track the history of image guided surgery in the NeuroImaging and Surgical Technology (NIST) lab at the Montreal Neurological Institute.  This talk will focus on the joy of working with curious, bright and hardworking students.  The NIST lab was the first to use frameless stereotaxic techniques with tracked intra-operative ultrasound to improve guidance during surgery while accounting for brain shift. The procedure matches intra-operative ultrasound to the pre-operative MRI data using image intensities or blood vessels as features to drive the registration. The result of this mapping is a deformation field that can be used to warp the pre-operative data to fit the anatomy of the patient during surgery, thus correcting for brain shift.  Over the past two decades, though the work of many students and fellows, this matching procedure has been improved by using additional anatomical landmarks, using simulated ultrasound, using statistically-driven intensity-based similarity functions and implemented with a fast GPU implementations. In addition to the brain, the NIST lab has developed tools to register preoperative spine CT to the patient, again with intra-operative ultrasound, to help in pedicle screw insertion when instrumenting one or more vertebrae. All these tools have been made publicly available as open source neuronavigation software known as IBIS (at http://ibisneuronav.org/) and templates and atlases (at http://nist.mni.mcgill.ca/atlases/).
-==== "Bénéfice de l'état de flow sur l'efficacité des distractions dans la prise en charge de l’anxiété préopératoire en anesthésie pédiatrique" ====
+**June 12, 2024 : Surgical workflow recognition of robotic-assisted hysterectomies: defense training** \\
-Présentation : Camille Tordet
+  * **Speaker:** Dario Tayupo\\
-"Les méthodes de distraction (jouet, dessin animé, jeu vidéo) ont été évaluées comme efficace dans la prise en charge de l’anxiété préopératoire des enfants. Les activités distractrices détournent l’attention des enfants des indices menaçants de la situation vers des activités et des pensées plus agréables. Toutefois, la variabilité d’efficacité de cette stratégie s’avère peu étudiée. En effet, si le bénéfice de la méthode de distraction s’explique par le transfert des ressources attentionnelles de la situation anxiogène vers l’activité distractrice, alors on devrait observer une variabilité d’efficacité selon le degré de ressources attentionnelles alloué sur l’activité. Ce travail cherche à analyser comment l’état de flow (état de concentration et d'absorption intense) peut fournir des explications, dans le but d’améliorer les distractions actuellement utilisées.
+**June 04, 2024 : Generalisation Capabilities of Machine-Learning Algorithms the Detection of the Subthalamic Nucleus in Micro-Electrode Recordings** \\
-Cette présentation abordera le contexte puis l’étude que nous avons menée au CHU de Rennes Sud, afin d’apporter des éléments de réponse à ces questions."
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** **Purpose**: Micro-electrode recordings (MERs) are a key intra-operative modality used during deep brain stimulation (DBS) electrode implantation, which allow for a trained neurophysiologist to infer the anatomy in which the electrode is placed. As DBS targets are small, such inference is necessary to confirm that the electrode is correctly positioned. Recently, machine learning techniques have been used to augment the neurophysiologist’s capability. The goal of this paper is to investigate the generalisability of these methods with respect to different clinical centres and training paradigms. **Methods**: Five deep learning algorithms for binary classification of MER signals have been implemented. Three databases from two different clinical centres have also been collected with differing size, acquisition hardware, and annotation protocol. Each algorithm has initially been trained on the largest database, then either directly tested or fine-tuned on the smaller databases in order to estimate their generalisability. As a reference, they have also been trained from scratch on the smaller databases as well in order to estimate the effect of the differing database sizes and annotation systems. **Results**: Each network shows significantly reduced performance (on the order of a 6.5% to 16.0% reduction in balanced accuracy) when applied out-of-distribution. This reduction can be ameliorated through fine-tuning the network on the new database through transfer learning, although even for these small databases, it appears that retraining from scratch may still offer equivalent performance as fine-tuning with transfer learning. However, this is at the expense of significantly longer training times. **Conclusion**: Generalisability is an important criterion for the success of machine learning algorithms in clinic. We have demonstrated that a variety of recent machine learning algorithms for MER classification are negatively affected by domain shift, but that this can be quickly ameliorated through simple transfer learning procedures that can be readily performed for new centres.
+**June 04, 2024 : Automated assessment of non-technical skills by heart-rate data** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** **Purpose**: Observer-based scoring systems, or automatic methods, based on features or kinematic data analysis, are used to perform surgical skill assessments. These methods have several limitations, observer-based ones are subjective, and the automatic ones mainly focus on technical skills or use data strongly related to technical skills to assess non-technical skills. In this study, we are exploring the use of heart rate data, a non-technical related data, to predict values of an observer-based scoring system thanks to random forest regressors. **Methods**: Heart rate data from 35 junior resident orthopedic surgeons were collected during the evaluation of a meniscectomy performed on a bench-top simulator. Each participant has been evaluated by two assessors using the Arthroscopic Surgical Skill Evaluation Tool (ASSET) score. A preprocessing stage on heart rate data, composed of threshold filtering and a detrending method, was considered before extracting 41 features: 12 on the time domain, 3 on the nonlinear domain, and 26 on the frequency domain. Then a random forest regressor has been optimized thanks to a randomized search cross-validation strategy to predict each score component. **Results**: The prediction of the partially non-technical related components presents promising results, with the best result obtained for the safety component with a mean absolute error of 0.24, which represents a mean absolute percentage error of 5.76%. The analysis of feature important allowed us to determine which features are the more related to each ASSET component, and therefore determine the underlying impact of the sympathetic and parasympathetic nervous systems. **Conclusion**: Heart rate data could be used for automatic skill assessment and more especially for the partially non-technical related components.
-===== Mardi 30 Mars 2021 13:00-14:00 =====
+**May 28, 2024 : Modélisation du mouvement de transfert d'embryon par simulation ** \\
+  * **Speaker:** Racky Sall\\
+  * **Sumarry:** **Contexte** : Transfert d'embryon étape finale du processus de fécondation in vitro avec un du taux de grossesse variable de 20 à 50 % entre praticiens **Objectif principal **: Analyser de façon comparative les différences dans la technique lors du transfert d’embryon entre les PPH et PPM par simulation échoguidée **Résultats **: 28 praticiens spécialistes en AMP issus de 6 centres ont été inclus.Les changements d’accélération sur le cathéter de transfert étaient significativement plus importants dans le groupe PPH lors de la réalisation des scénarios E et C avec respectivement 10496 cm.s-3 ± 12643 versus 2881 cm.s-3 ± 2538 pour les PPM p =0,007 et 4942 cm.s-3  ± 4845 versus 2867 ± 2153 p = 0,06.En analyse de sous groupe (n=15),la vitesse d’éjection était de 0,44 ml.s-1 ± 0,2 pour les praticiens à performance haute lors de la réalisation du scénario A, versus 0,7 ml.s-1 ± 0,4 dans le groupe PPM, p = 0,02. Nous n'avons pas mis en évidence de différence entre PPH et PPM concernant la durée, la position du cathéter lors du transfert, le nombre d'atteinte du fundus et la gestuelle.
-==== "Brain correlates of behavioural disinhibition in behavioural variant frontotemporal dementia." ====
+**May 21, 2024 : Surgical data Science at Technion** \\
-Présentation : Delphine Tanguy
+  * **Speaker:** Schlomi Laufer from Technion University, Israel\\
-"Disinhibition is a core symptom in neurodegenerative diseases, in particular in fronto-temporal dementia (FTD), and a major cause of stress for caregivers. However, the concept of this symptom is hard to disentangle: while a distinction between behavioural and cognitive disinhibition is common, an operational definition of behavioural disinhibition remains unclear. Therefore, available assessments of these behavioural disorders are imprecise and the corresponding neuroanatomical correlates are non-univocal.Thus, we aimed to characterise the anatomical networks underlying different subtypes of behavioural disinhibition. For this purpose, we used an original semi-ecological task assessing two specific dimensions of behavioural disinhibition, such as compulsivity and social disinhibition, in 17 behavioural variant of FTD patients and 18 healthy controls, associated with classic neuropsychological tests and brain imaging (voxel-based morphometry for the grey matter, tractography for the white matter). Compulsivity correlated with right temporal regions atrophy and with alterations of the bilateral cingulum and uncinate fasciculus, the right inferior longitudinal fasciculus and the right arcuate fasciculus. Social disinhibition was associated to huge bilateral frontal atrophy and impairments in the cingulum, the forceps minor and the left uncinate fasciculus. By combining ecological behavioural analyses with neuroanatomy, we identified two subtypes of behavioural disinhibition associated with differential neural networks."
+**May 14, 2024 : Summer Noon sharing Planning** \\
+  * **Speaker:** Arnaud Huaulmé\\
-===== Mardi 23 Février 2021 13:00-14:00 =====
+**May 07, 2024 : nan** \\
+  * **Speaker:**  Patrick Archambault from  Université de Laval , Canada\\
-==== " Automatic Cortical Target Point Localisation in MRI for Transcranial Magnetic Stimulation via a Multi-Resolution Convolutional Neural Network " ====
+**April 23, 2024 : Review Exercice** \\
-Présentation : John S H Baxter
+  * **Speaker:** All Team\\
+  * **Sumarry:** The exercice involves reviewing a scientific paper submitted to an international conference, including accepted and rejected papers. The objective is to learn what is required for a high-quality review, thereby improving both your reviewing skills and your own writing abilities by avoiding common mistakes you've identified
-" Transcranial Magnetic Stimulation (TMS) is a growing therapy for a variety of psychiatric and neurological disorders that arise from or are modulated by cortical regions of the brain represented by singular 3D target points. These target points are often determined manually with assistance from a pre-operative T1-weighted MRI, although there is growing interest in automatic target point localisation using an atlas. However, both approaches can be time-consuming which has an effect on the clinical workflow and the latter does not take into account patient variability such as the varying number of cortical gyri where these targets are located. This paper proposes a multi-resolution convolutional neural network for point localisation in MR images for a priori defined points in increasingly finely resolved versions of the input image. This approach is both fast and highly memory efficient, allowing it to run in high-throughput centres, and has the capability of distinguishing between patients with high levels of anatomical variability. Preliminary experiments have found the accuracy of this network to be 7.26+5.30 mm, compared to 9.39+4.63 mm for deformable registration and 6.94+5.10 mm for a human expert. The human-level performance of this network indicates that it can improve TMS planning by automatically localising target points in seconds, avoiding more time-consuming registration or manual point localisation processes. "
+**April 16, 2024 : L'état de l'art des LLM dans le médical, et direction du projet LLM chirurgical** \\
+  * **Speaker:** Vinnie Souarn\\
+  * **Sumarry:** Dans le domaine médical, les LLM (large language models) commencent à prendre beaucoup d'ampleur dans les innovations actuelles. Dans cette présentation, je vais faire une introduction au sujet des LLM et un état de l'art des LLM dans le médical. Enfin je vais discuter de la direction du projet que l'on m'a confié qui consiste à construire un LLM capable d'accomplir des tâches dans le domaine chirurgical, et plus précisément les hystérectomies.
-===== Mardi 16 Février 2021 13:00-14:00 =====
+**April 09, 2024 : Foveolar drusen decrease fixation stability in pre-symptomatic AMD.** \\
+  * **Speaker:** Josselin Gautier\\
+  * **Sumarry:** **Purpose:** To link changes of fixational eye movements (FEM) in controls and patients with foveal drusen using adaptive optics retinal imaging to find anatomo-functional markers for pre-symptomatic AMD. **Design:** A population-based cohort study with 7 young controls, 4 older controls and 16 presymptomatic AMD patients with foveal drusen. **Methods:** A high speed research-grade adaptive optics flood illumination ophthalmoscope was used for monocular retinal tracking of fixational eye movements. The system allows for sub-arcminute resolution, high-speed and distortion-free imaging of the foveal area. Early signs of AMD were documented using gaze-dependent imaging on a clinical-grade AO-FIO. Main outcome measures: Microsaccade amplitude, drift diffusion coefficient and fixation stability across participants, and in the case of presymptomatic AMD participants, the relationship between these variables and retinal structure characteristics such as drusen size and eccentricity. **Results:** FEM were measured with high precision (RMS-S2S=0.0015° on human eyes) and small foveal drusen (median=60μm) were detected with high contrast imaging. Microsaccade amplitude, drift diffusion coefficient and ISOline Area (ISOA) were significantly larger for patients with foveal drusen compared with controls. Among the drusen participants, microsaccade amplitude was correlated to drusen eccentricity from the center of the fovea.Conclusions: A novel high-speed high-precision retinal tracking technique allowed for the characterization of FEM at the microscopic level. Foveal drusen altered fixation stability, resulting in compensatory FEM changes. Eye movement analysis with flood imaging provides robust description of both functional and structural signs of early age-related changes.
-==== " PETRAW: PEg TRAnsfer Workflow recognition by different modalities " ====
+**April 02, 2024 : Multimodal physiological sensor-based analysis of surgical non technical-skills in training environments** \\
-Présentation : Arnaud Huaulmé
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** This study investigates the use of multimodal analysis to assess non-technical skills through physiological sensors. Our approach leverages data from ECG, EMG, Accelerometer, and Gyroscope sensors to evaluate individual modalities and combine outputs from different sensors. The results provide insights into the effectiveness of this approach for assessing non-technical skills.
-" Automatic and online recognition of surgical workflows is mandatory to bring computer-assisted surgery (CAS) applications inside the operating room. According to the type of surgery, different modalities could be used for workflow recognition. In the case of robotic-assisted surgeries and virtual reality training sessions, video and kinematic data are easily available. However, even if these modalities are available, numerous methods on state of art only focus on one of them. Last year we submitted the MISAW sub-challenge as part of EndoVis at MICCAI2020 (challenge description and results available at https://www.synapse.org/MISAW, paper under writing), offering to participant to combine both modalities for the workflow recognition. To the best of our knowledge, there are very few studies about the added value to combine multiple modalities. Whereas, some study as demonstrate that the addition of external information improve the recognition, as the presence of tools
+**March 26, 2024 : Validation of a generic Surgical Process Model: The super interesting case of the robot-assisted hysterectomy** \\
+  * **Speaker:** Soline Galuret\\
+  * **Sumarry:** When several descriptions of individual surgeries (iSPM: individual Surgical Process Model) are available within a homogeneous set of surgical procedures, they can be combined into a single model as a graph named a generic Surgical Process Model (gSPM). Such gSPM has the potentiality to capture the variability of a surgery, and provide a computable process model that allows for quantitative analysis of surgical processes. The gSPM can also be used to follow the state of an ongoing surgery and give access to the possible upcoming steps. Using knowledge elicitation from an expert surgeon, a gSPM of the robotic-assisted hysterectomy has been built and now needs to be validated, This presentation will focus on this ongoing validation step, using both experts knowledge (by Delphi consensus) and experts practice (by comparing gSPM and iSPMs). As we are still unsure on the methods to use (especially for the Delphi), your opinions and ideas would be a great help.
-PETRAW is a sub-challenge of ENDOVIS 2021 currently on minor revision for MICCAI2021. PETRAW focuses on the comparison of 3 modalities (video, kinematic, and segmentation) and their combination on surgical workflow recognition. On this noon sharing, I will present the challenge design and probably partial results."
+**March 26, 2024 : Soft-Cesar: Presentation study** \\
+  * **Speaker:** Caroline Béridot\\
-===== Mardi 9 Février 2021 13:00-14:00 =====
+**March 19, 2024 : ALIGN Application presentation** \\
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** With the goal of providing a postural and ergonomic analysis for analysis and for teaching, the ALIGN (Advanced Learning Interface for surGical ergoNomics) was designed. This application combines the various steps separating videos of the surgeon from quantitative results using a version of OpenPose and post-processing adapted to our surgical application. One these steps are performed, the results are represented in graphical, avatar-based form with respect to different anatomical zones as well as a textual summary to which advice can be appended.
-==== " Preliminary results on the characterization of PD from DT images on the PPMI dataset by means of CNNs" ====
+**March 19, 2024 : Surgical ergonomics and posture assessment: A review on methodologies and applications in an educational context** \\
-Présentation : Alfonso Estudillo Romero
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** Ergonomics is the discipline of analyzing human posture, taking into account the design of furniture or equipment, with the aim of optimizing well-being and overall performance. Initially used in industry, it was applied to surgery by observations in operating theaters. This led to the identification of parameters explaining the workload-related musculoskeletal disorders (WRMSD) experienced by surgeons and demonstrated the need for increased education in this field. The aim of this review is to explore the methods used to assess posture and the contexts in which they were analyzed, highlighting the parameters that promoted WRMSD and focusing on the educational context. For that, two queries were performed on PubMed returning 1104 papers, two exclusion criteria ( : year of publication and type of paper) were used to select relevant papers for the study. After this pre-selection, 262 abstracts were screened, selecting 72 relevant papers that have been read in their entirety. This resulted in a selection of 46 papers published between 2011 and 2022. It showed that the WRMSD have consequences on the professional activities for 34.98%±12.88% surgeons. This is combined with 10.19%±6.23% of surgeons taking a day off from hospital due to WRMSD and 16.69%±15.27% of surgeons attesting to taking breaks during surgeries. With only 22.8%±10.14% of surgeons having received ergonomic learning. These results highlighted the importance to study the WRMSD in surgery and to increase the ergonomic learning.
-" We present our preliminary results on the analysis of diffusion tensor images (DTI) by means of a Convolutional Neural Network (CNN) to classify Parkinsonian patients (PD) and healthy controls (HC) from brain images.  An analysis of the whole population registered in a common space is proposed to compute some of the classical anisotropy measures in a voxel-based approach. Moreover, we retrieved the back-propagated gradients of these images through the CNN to understand how sensitive the CNN is to some anisotropy measures at some particular regions. "
+**March 12, 2024 : Crisis management in the operating room: A systematic review of simulation training to develop nontechnical skills** \\
+  * **Speaker:** Inas Redjem\\
+  * **Sumarry:** Crises in operating room settings, often stemming from human factors, can lead to adverse events, thereby jeopardizing patient safety. Non-technical skills training through simulation appears to hold promise for healthcare professionals in effectively managing such potential crisis situations. This systematic review outlines simulation methods, target audiences, non-technical skills, crisis scenarios, and metrics for managing operating theater crises. Medline, PsycInfo and Web of Science databases were searched in March 2024 as per PRISMA guidelines, yielding 29 eligible articles. Results showcase predominance of high-fidelity simulations, and multidisciplinarity across surgical specialties. Training focused on communication, teamwork and situation awareness, addressing patient deterioration, equipment malfunctions, and team-related failures. Assessments reached Kirkpatrick’s Level 3 at best, demonstrating positive training impact via reactions and learning metrics rather than behavior and organizational results. Despite their effectiveness, current evaluation practices exhibit considerable methodological variations. Standardizing simulation techniques, defining non-technical skills clearly, and adopting immersive assessment approaches, could enhance training effectiveness. This has implications for interprofessional education, comprehensive evaluation frameworks, technological integration and skill transfer to real-world settings, ultimately improving patient safety.
-===== Mardi 2 Février 2021 13:00-14:00 =====
+**March 05, 2024 : Evaluation de l'utilisabilité de l'outil de segmentation interactif auprès de neurochirurgiens, neurologues et neuroradiologues** \\
+  * **Speaker:** Enora Giffard\\
+  * **Sumarry:** Cette réunion sera l'occasion de vous montrer en avant-première l'outil de segmentation interactif des structures sous-corticales d'intérêt. Cet outil vise à offrir une alternative au recalage actuellement utilisé en modélisation péri-opératoire pour la stimulation cérébrale profonde par exemple. Nous supposons que l'interactivité améliorera l'utilisabilité ainsi que l'acceptabilité car, bien que relativement précis, en cas d'erreur du modèle le praticien peut corriger le résultat mais également relancer le modèle avec d'autres données de localisation. Ainsi cet outil pourrait réduire la fréquence des erreurs ainsi que du recours à la segmentation entièrement manuelle faute de résultats satisfaisants. Cette réunion sera également l'occasion de discuter avec vous de l'expérience envisagée pour évaluer l'utilisabilité et de profiter de votre expérience et de vos conseils toujours bienvenus.
-==== " Extending Deep Neural Networks with Bayesian Inference and Recurrent Layers for Localizing the Subthalamic Nucleus from Micro-Electrode Recordings" ====
+**February 20, 2024 : Fine eye movements and pupil dynamic to monitor change in cognitive workload during surgery** \\
-Présentation : Thibault Martin
+  * **Speaker:** Josselin Gautier\\
+  * **Sumarry:** In this talk we will review the existing works aiming to monitor surgeons' task workload during surgical procedures. One one hand, pupil diameter has been shown to be a sensitive index of the level of demands associated with a wide range of cognitive tasks such as mental arithmetic, perceptual discrimination, sustained attention, visual search, working memory, problem solving and language processing. However pupil dynamic is a slow process and it remains challenging to evaluate in a continuous manner. Distinguishing between cognitive or motor complexity and motor precision during surgical tasks appears crucial, as they affect the pupil size oppositely. Pupil diameter may not be an appropriate index of workload in tasks which vary in both complexity and precision, but further appropriate reference points of the surgical tool movement might be identified in this regard. On the other hand, fixational eye movements have also received a lot of attention over the past 20 years. They are known to counteract visual fading, scan small and informative visual regions, improve visual acuity by precisely relocating our foveola, and also reflect mental fatigue. Limited research has been conducted in the field of surgery, with however important findings: markers such as saccadic peak velocity  are reliable indicators of subjective fatigue. Surgical performance (evaluated objectively and subjectively) appears however not impacted by surgeon resident’s fatigue. It remains to be understood what the surgeons with high levels of fatigue are accepting to trade for maintaining similar overall surgical performance: motor precision vs motor velocity, or something else ?
-" Deep brain stimulation (DBS) is an interventional treatment for Parkinson's disease which involves the precise positioning of stimulation electrodes within particular subcortical anatomy. Although originally identified via imaging, additional inter-operative guidance is necessary to localize the target anatomy. Analysis of Micro-Electrode Recordings (MERs) allows for a trained neurophysiologist to infer the underlying anatomy at a particular electrode position using human audition, although it is subjective and requires a high degree of expertise. This project aims to develop and validate a deep neural network to assist in MER analysis during DBS which can use arbitrary length MERs while providing feedback to the neurophysiologist as to the model's certainty. We evaluate six different deep learning based classifiers which can use arbitrary length MERs for Sub-Thalamic Nucleus (STN) segmentation, finding a particular Baysian network to perform the best. With a view to providing decision support, the use of Bayesian inference has also made it possible to interpret the level of confidence in the predictions underlying the predictive model. This work represents a step forward in integrating automated analysis of MERs into the DBS surgical workflow by automatically finding and exploiting MER in a data-driven predictive model. "
+**February 13, 2024 : Critical review of the literature: the case of embryo transfer** \\
+  * **Speaker:** Racky Sall\\
+  * **Sumarry:** Racky va nous présenter une revue critique de la littérature qui se concentre sur deux articles: "Simulation training for embryo transfer: findings from the American Society for Reproductive Medicine Embryo Transfer Certificate Course'' et "Embryo transfer training in fellowship: national and institutional data."
-===== Mardi 5 Janvier 2021 13:00-14:00 =====
+**February 06, 2024 : Surgical workflow recognition of robotic assisted hysterectomies: State of the art** \\
+  * **Speaker:** Dario Tayupo\\
+  * **Sumarry:** Je vais commencer par présenter le problème de la reconnaissance automatique de workflow chirurgical, et les difficultés associées à l'utilisation de données cinématiques et vidéo. Je vais ensuite présenter différents modèles qui peuvent être utilisés pour cette tâche comme les modèles statistiques (Hidden markov models, Dynamic time warping, et Conditional random fields), et les modèles de deep learning (réseaux convolutionnels, LSTM, transformers), et discuter des avantages et inconvénients de chaque modèle.
-==== " Place de l’Apprentissage de la Chirurgie Arthroscopique utilisant la Simulation en Réalité Virtuelle (VR) à propos d’un Geste : la Méniscectomie - MENISIM-VR" ====
+**February 06, 2024 : Effect of the prior distribution on a Bayesian model for errors of type for transcranial magnetic stimulation** \\
-Présentation : Alexandre Tronchot
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Measuring errors in neuro-interventional pointing tasks is critical to better evaluating human experts as well as machine learning algorithms. If the target may be highly ambiguous, different experts may fundamentally select different targets, believing them to refer to the same region, a phenomenon called an error of type. Recent work in measuring these errors of type in transcranial magnetic stimulation has led to a reference-free Bayesian model that can estimate the relevant model parameters from clinical data. However, this model fundamentally relies on a prior distribution. The goal of this paper is to investigate the effect of changing this distribution in both simulated and clinical data. Our results show that using a poly-geometric prior distribution allows for analytic solvability as well as the capacity to minimise spurious modes introduced by the basic model. This significantly improves computational time as well as ensuring that estimates for the number of incorrect distractor points is less sensitive to noise in the data and is more reasonable without significant bias in estimating the rate in which the annotators select the correct point.
-"Les dernières années ont été marquées par d'importantes avancées dans la formation initiale des jeunes chirurgiens avec du temps alloué supplémentaire et de nouveaux outils pédagogiques. Toutefois, le quotidien reste essentiellement occupé par le temps de service. Paradoxalement, les internes vont être mis en responsabilité plus vite avec un temps passé à l'hôpital plus court. La formation initiale doit donc à la fois assurer sa mutation et rester efficiente en trouvant des compléments et alternatives au traditionnel compagnonnage. La simulation est l'un des outils proposés pour cela, et elle a déjà fait ses preuves dans le domaine comportemental. Son évolution vers la réalité virtuelle (VR) est maintenant proposée pour la formation procédurale car elle offre un outil à la frontière entre réalités théorique et pratique et, surtout, inlassablement reproductible. La chirurgie arthroscopique est particulièrement adaptée à cette simulation VR du fait de son retour visuel per-opératoire sur écran 2D. Toutefois, et bien qu'il y ait de plus en plus d'articles scientifiques parlant de l'intérêt de la simulation VR en chirurgie arthroscopique, peu rapportent sa validité lors de la transposition des performances du simulateur vers le patient réel. Montrer que l'étudiant en progressant sur simulateur devient également performant au bloc opératoire serait une avancée considérable dans la formation médicale du troisième cycle, correspondant parfaitement aux demandes des Ministères de la Santé et de l'Enseignement Supérieur et la Recherche à la fois en termes de sécurité patient ("Jamais la première fois sur le patient"), mais aussi de sécurité du praticien et d'enjeux économiques de formation."
+**January 30, 2024 : Debriefing of the [[confs_page:xr4medsim|XR4MedSim Workshop]]** \\
+  * **Speaker:** All Team\\
-===== Mardi 8 Décembre 2020 13:00-14:00 =====
+**January 23, 2024 : Spring Noon sharing Planning** \\
+  * **Speaker:** John Baxter\\
-==== "Hystérectomie : indications, modalités et apports de la chirurgie robot assistée." ====
+**January 09, 2024 : Preparation of the [[confs_page:xr4medsim|XR4MedSimWorkshop]]** \\
-Présentation : Sonia Guerin
+  * **Speaker:** XR4Medsim  organisation Team\\
+  * **Sumarry:** In preparation for the upcoming [[confs_page:xr4medsim|XR4Medsim workshop]], jointly organized by Medicis, IRISA, and University Rennes 2, this week's Noon sharing session will focus on event organization. We will present an overview of the day's schedule and highlight key organizational aspects where participant input is crucial to ensure a successful and engaging experience."
-"Hysterectomy is the most commonly performed gynecological procedure in high income countries. Eight-seven percent of indications are benign diseases. Several surgical approaches are possible, each with its own advantages and disadvantages. With the arrival of the surgical robot, it is now possible for us to study precisely the gestures performed by the surgeon thanks to kinematics and video data analysis.
-Initially, we will look at the indications, approaches and complications of hysterectomy before discussing the contribution of kinematic and video data in general surgery and in hysterectomy in particular."
-===== Mardi 1er Décembre 2020 13:00-14:00 =====
+===== 2023 =====
+**December 19, 2023 : Répétition de soutenance de thèse** \\
+  * **Speaker:** Thibault Martin\\
-==== "A semantic database for integrated management of image and dosimetric data in low radiation dose research in medical imaging" ====
+**November 28, 2023 : Comment choisir ses métriques en analyse d'images biomédicales? Metrics reloaded, un consensus d'experts pour des décisions éclairées** \\
-Présentation : Bernard Gibaud
+  * **Speaker:** Enora Giffard\\
-"Medical ionizing radiation procedures and especially medical imaging are a non negligible source of exposure to patients. Whereas the biological effects of high absorbed doses are relatively well known, the effects of low absorbed doses are still debated. This work presents the development of a computer platform called Image and Radiation Dose BioBank (IRDBB) to manage research data produced in the context of the MEDIRAD project, a European project focusing on research on low doses in the context of medical procedures. More precisely, the paper describes a semantic database linking dosimetric data (such as absorbed doses to organs) to the images corresponding to X-rays exposure (such as CT images) or scintigraphic images (such as SPECT or PET images) that allow measuring the distribution of a radiopharmaceutical.
+**November 21, 2023 : Mastering the Move: Decoding Embryo Transfer Techniques for Optimal IVF Success in Simulation setting** \\
+  * **Speaker:** Racky Sall\\
-The main contributions of this work are: 1) the implementation of the semantic database of the IRDBB system and 2) an ontology called OntoMEDIRAD covering the domain of discourse involved in MEDIRAD research data, especially many concepts from the DICOM standard modelled according to a realist approach."
+**November 14, 2023 : ÉTUDE ANATOMIQUE DE L’INNERVATION UTÉRINE : APPLICATION À L’ENDOMÉTRIOSE** \\
+  * **Speaker:** Léa Roux, Audrey Astruc\\
+  * **Sumarry:** Cette étude réunit les CHU de Rennes et d’Angers pour explorer l'analyse de l'innervation utérine en relation avec les symptômes de pathologies bénignes telles que l'endométriose, l'adénomyose et les fibromes. L'originalité de cette étude repose sur la corrélation directe entre la structure nerveuse de l'utérus avec les expériences vécues par les patientes. Ceci pourrait ouvrir de nouvelles voies pour l'amélioration des traitements et le soulagement des symptômes.
+**November 14, 2023 : Le jour des morts au Mexique offre un riche mélange de cultures** \\
+  * **Speaker:** Alfonso Estudillo Romero\\
+  * **Sumarry:** Est-il vrai que les Mexicains se moquent et rient de la mort ? N'ont-ils pas peur d'elle ? Je vais aborder le Jour des Morts au Mexique, en commençant par les célébrations pratiquées dans les cultures précolombiennes jusqu'à nos jours où les autels, les cimetières, la nourriture, les boissons, les fleurs, le papel picado, la musique et les costumes font partie de l'une des célébrations les plus attendues au Mexique.
-===== Mardi 10 Novembre 2020 13:00-14:00 =====
+**November 07, 2023 : Multimodal physiological sensor-based analysis of surgical non-technical skills in training environments: The case of heart rate** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Surgical simulation has become an important part of the surgeon training program. Simulation is mostly performed autonomously and only receives feedback on evaluation measures based on outcomes that can be directly measured by the simulators: execution time, instrument collisions, workspace overlap, length of movements, etc. However, this information is not sufficiently informative and does not always reflect surgical expertise. To qualify the expertise, many scores exist, such as the ASSET or GOALS scores. These scores aim at standardizing the evaluation of expertise thanks to a list of important points such as dexterity or safety. These scores are evaluated by experts who observe the learner. They are therefore subjective and time-consuming. It has been shown that kinematic data can be used to partially identify the GOALS score automatically. However, the non-technical skills highlighted by these scores, such as autonomy or quality of the procedure, are not only related to the movement of the instruments. To qualify the expertise, many scores exist, such as the ASSET or GOALS scores. These scores aim at standardizing the evaluation of expertise thanks to a list of important points such as dexterity or safety. These scores are evaluated by experts who observe the learner. They are therefore subjective and time-consuming. It has been shown that kinematic data can be used to partially identify the GOALS score automatically. However, the non-technical skills highlighted by these scores, such as autonomy or quality of the procedure, are not only related to the movement of the instruments. In this noon sharing, I will present the first results obtained from heart rate data. The aim was to see whether classification or regression could be used to determine Virtamed simulator scores (Alexandre's MENISIM1 study) or ASSET scores (MENISIM 2 study).
-==== "Flexible recurrent neural network for Audio-Visual sequence analysis" ====
+**October 24, 2023 : Le langage chez le primate non humain** \\
-Présenté par : Tsiry Mayet
+  * **Speaker:** Soline Galuret\\
+  * **Sumarry:** Des propriétés universelles du langage sont observées dans toutes les cultures humaines. On peut citer par exemple l’apprentissage social, l’imitation, la sémantique, la syntaxe et les règles de conversations. Le partage de ces caractéristiques nous amène à nous interroger sur les bases biologiques de ces propriétés et sur la recherche d’une origine évolutive commune. Le langage étant avant tout social, il n’a laissé que peu de traces sur les fossiles. Nous pouvons alors rechercher ses origines au-delà de l’humain : chez nos plus proches cousins vivants, les primates non humains. Aujourd’hui, on dit que le langage est le dernier élément qui sépare l’humain de l’animal, mais qu’en est-il vraiment ?
-"Deep learning models are now brought closer to the user rather than running in a distant cloud, helping to reduce latency, network congestion, and improving data security and privacy. However, smartphones and user devices impose additional constraints such as limited computation or energy. Handling these constraints has become an active research topic. User devices can also host multiple processes running at the same time and starting or stopping abruptly, modifying the constraints affecting the processes. Few works have considered models that can be modified at run time to adapt to an evolving computational limit."
+**October 03, 2023 : Effect of the prior distribution on a Bayesian model for errors of type for transcranial magnetic stimulation** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Measuring errors in neuro-interventional pointing tasks is critical to better evaluating human experts as well as machine learning algorithms. If the target may be highly ambiguous, different experts may fundamentally select different targets, believing them to refer to the same region, a phenomenon called an error of type. Recent work in measuring these errors of type in transcranial magnetic stimulation has led to a reference-free Bayesian model that can estimate the relevant model parameters from clinical data. However, this model fundamentally relies on a prior distribution. The goal of this paper is to investigate the effect of changing this distribution in both simulated and clinical data. Our results show that using a poly-geometric prior distribution allows for analytic solubility as well as the capacity to minimise spurious modes introduced by the basic model. This significantly improves computational time as well as ensuring that estimates for the number of incorrect distractor points is less sensitive to noise in the data and is more reasonable without significant bias in estimating the rate in which the annotators select the correct point.
-===== Mardi 20 Octobre 2020 13:00-14:00 =====
+**October 03, 2023 : Bringing Vision science to the Operating Room: analyses of movement, performance and human factor; applications for surgical assistance and training** \\
+  * **Speaker:** Josselin Gautier\\
+  * **Sumarry:** In this talk I will describe recent works relying on retinal imaging instruments to understand basic vision. Adaptive Optics ophthalmoscopes track the finest movements of the eye during simple fixation tasks or visual recognition tasks whose stimuli are laser-projected onto the eye. Results illustrate individual strategies relying on retinal landmarks and microsaccadic movements at a cellular scale. In another study, related oculomotor biomarkers identified at the earliest step of age-related macular degeneration reveal new links between structural defects and their functional consequences. In patients with myopia, measured angular variation of contrast sensitivity and individual cone angulation could provide new horizons to better manage their vision care. Psychophysical studies in controlled conditions are easily transposable to simulated, assisted or real surgery where time, fine movement (eye-hand coordination, visuo-motor control) and performance (cognitive workload, attention, fatigue) are of critical importance. Some perspectives from low-level cues to automatic semantic retrieval for surgical training and assistance will be drawn.
-==== "Data driven methods to support decision making in Deep Brain Stimulation for Parkinson’s Disease " ====
+**September 28, 2023 : Simulation préopératoire sur maquettes 3D avant reprise acétabulaire de prothèse totale de hanche utilisant un implant trabecular métal, une étude prospective** \\
-Présenté par : Maxime Peralta (Répétition de soutenance de thèse)
+  * **Speaker:** Michel Drouineau\\
+  * **Sumarry:** La reprise de PTH pour descellement acétabulaire est complexe et discutée. Le comblement des pertes de substances osseuses (PSO) par cup et augment en trabecular metal ou tantalum laisse espérer une plus grande survie prothétique. L’étude RPTH-SIM évalue la reproductibilité (face-validity) d’un atelier de simulation préopératoire sur maquettes 3D à échelle réelle en comparant les types implants posés, tailles ainsi que la classification de Paprosky effectuée en simulation par rapport à la chirurgie du patient.
-===== Mardi 13 Octobre 2020 13:00-14:00 =====
+**July 04, 2023 : Introduction de l'utilisation d'apprentissage automatique... en archéologie!** \\
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** L'intelligence artificielle est maintenant utilisée dans de nombreux domaines : l'aéronautique, la médecine, la physique, les langues, etc. Cependant, certaines utilisations sont moins connues et plus récentes telles que l'IA au service de l'archéologie. L'apport de l'IA dans ce domaine consiste en du traitement d'image, de textes, de reconstruction et devient un réel outil pour les archéologues.
-==== "MISAW - Part of the Endoscopic Vision Challenge" ====
+**June 27, 2023 : Tour de table + retour sur la conférence CARS 2023** \\
-Présenté par : Arnaud Huaulmé
+  * **Speaker:** Tour de table\\
-"Automatic and online recognition of surgical workflows is mandatory to bring computer-assisted surgery (CAS) applications inside the operating room. According to the type of surgery, different modalities could be used for workflow recognition. In the case where the addition of multiple sensors is not possible, the information available for manual surgery is generally restricted to video-only. In the case of robotic-assisted surgery, kinematic information is also available. It is expected that multimodal data would make easier automatic recognition methods.
+**June 13, 2023 : Brief review on CUD principles, neuroimagery methods and current biomarker searching results.** \\
+  * **Speaker:** Alfonso Estudillo-Romero\\
+  * **Sumarry:** The proposals of the cerebral pathways and the mechanisms underlying addiction disorders are not something new. In general, subjects' substance abuse, as in the case of cocaine use disorder (CUD), will exhibit not only physical alterations in white (WM) and gray matter (GM) but also cognitive, behavioral and emotional changes. To address the topic in this talk, we first need to briefly discuss the circuitry involved in generally speaking an addiction as well as some of the terms used in the literature. Secondly, we will see the state of the art regarding the methods that have helped to explain the disorder from the neuroimagery perspective. Finally, we will discuss some of the results we have obtained in the lab, in particular on the unraveling of cocaine biomarkers using machine learning methods.
-The “MIcro-Surgical Anastomose Workflow recognition” (MISAW) sub-challenge provides a unique dataset for online automatic recognition of surgical workflow by using both kinematic and stereoscopic video information on a micro-anastomosis training task. Participants are challenged to recognize online surgical workflow at different granularity levels (phases, steps, and activities) by taking advantage of both modalities available. Participants can submit results for the recognition of one or several granularity levels. In the case of several granularities, participants are encouraged (but not required) to submit the result of a multi-granularity workflow recognition, i.e. recognize different granularity levels thanks to a unique model."
+**May 23, 2023 : Répétition des présentations pour CARS 2023 : "Reference-free Bayesian model for pointing errors-of-type in neurosurgical planning." (John Baxter)** \\
+  * **Speaker:** John Baxter\\
-===== Mardi 22 Septembre 2020 13:00-14:00 =====
+**May 23, 2023 : Répétition des présentations pour CARS 2023 : "Gaze behavior is related to objective technical skills assessment during virtual reality simulator based surgical training: a proof of concept** \\
+  * **Speaker:** Soline Galuret\\
-==== "Characterisation of three clinical-neurological subtypes of the bvFTD based on inhibition deficit symptoms assessed through an ecological approach" ====
+**May 16, 2023 : Exploring the Impact of a Virtual Reality Operating Room Visit on Nursing Students' Anxiety, Self-Efficacy, and Knowledge** \\
-Présenté par : Delphine Tanguy
+  * **Speaker:** Inès Redjem\\
-===== Mardi 15 Septembre 2020 13:00-14:00 =====
+**April 28, 2023 : Review Exercice** \\
+  * **Speaker:** All Team\\
+  * **Sumarry:** The exercice involves reviewing a scientific paper submitted to an international conference, including accepted and rejected papers. The objective is to learn what is required for a high-quality review, thereby improving both your reviewing skills and your own writing abilities by avoiding common mistakes you've identified
-==== "Review of my work" ====
+**April 04, 2023 : Utilisation de sEMG dans le contexte de la formation chirurgicale par simulation** \\
-Présenté par : Kevin Le Mut
+  * **Speaker:** Chenji Li\\
+  * **Sumarry:** Robotic surgery represents a major breakthrough in the evolution of medical technology. Accordingly, efficient skill training and assessment methods should be developed to meet the surgeon’s need of acquiring such robotic skills over a relatively short learning curve in a safe manner. Different from conventional training and assessment methods, we aim to explore the surface electromyography (sEMG) signal during the training process in order to obtain semantic and interpretable information to help the trainee better understand and improve his/her training performance. As a preliminary study, motion primitive recognition based on sEMG signal is studied in this work. Using machine learning (ML) technique, it is shown that the sEMG-based motion recognition method is feasible and promising for hand motions along 3 Cartesian axes in the virtual reality (VR) environment of a commercial robotic surgery training platform.
-"During 1 year of contract I carried out various works at MEDICIS. My main objective was the annotation of hysterectomy videos but I also participated in the annotations of the MISAW project and started to develop an application. In addition to this, various tasks were added to complete my work such as annotation protocol build on SurgePlan. The year 2020 was full of hazards that slowed down the progress of the work."
+**March 21, 2023 : Présentation des objectifs et du déroulement du robotic training center au sein du labo d'anatomie.** \\
+  * **Speaker:** Arnaud Huaulmé & Soline Galuret\\
+  * **Sumarry:** Soline et moi-même vous présenterons les objectifs et le déroulement du robotic training center qui a actuellement lieu au sein du labo d'anatomie. Dans ce context, nous avons la chance de pouvoir bénéficier du Mercredi 22 après-midi des deux robot DaVinci. La seconde partie de la présentation aura pour objectif de vous présentez le planning de ce mercredi et des tests que nous mettrons en place.
-===== Mercredi 09 Septembre 2020 16:00-17:00 =====
+**March 14, 2023 : Point sur l'avancée des travaux de thèse** \\
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** La présentation portera sur mes travaux de thèse sur l'analyse de posture des chirurgiens en exercices de simulation grâce à l'algorithme OpenPose. Deux axes seront abordés : le tracking des chirurgiens après la détection OpenPose, la validation des résultats obtenus. Ces deux points sont essentiels pour assurer une analyse juste des postures des chirurgiens et permettent d'avoir des bases solides pour le calcul des métriques et la partie pédagogique du projet.
-==== "Shared meeting with the VASST team" ====
+**March 14, 2023 : Tentative de ré-entraînement du réseau OpenPose avec les données chirurgicales, et présentation des avancées d'une revue de littérature** \\
-Présenté par : Thibaut Dognon
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** La présentation sera axée sur les avancées de la thèse sur la détection et l'analyse de posture des chirurgiens dans le cadre de l'étude MENISIM. Une première partie sera allouée à la détection en elle même, avec des résultats des essais de ré-apprentissage du réseau de neurones. La deuxième partie sera sur l'avancée de l'état de l'art, la méthodologie employée, les articles sélectionnés, les lectures à poursuivre ainsi que des résultats représentant les diverses études.
-===== Mercredi 08 Juillet 2020 16:00-17:00 =====
+**March 07, 2023 : Présentation des nouveaux résultats sur la synthèse des signaux MER + expérience participative** \\
+  * **Speaker:** Thibault Martin\\
-==== "Shared meeting with the VASST team" ====
+**February 14, 2023 : Un bloc opératoire en réalité virtuelle pour former les professionnel.le.s et étudiant.e.s de santé aux compétences non techniques : Le travail des 3 prochaines années.** \\
-Présenté par : Maxime Peralta
+  * **Speaker:** Inès Redjem\\
+  * **Sumarry:** Un événement indésirable au bloc opératoire désigne tout incident ou accident survenu pendant une intervention chirurgicale, qui peut entraîner des conséquences négatives pour la santé des patients. Ces événements sont fréquemment causés par des erreurs humaines, qui sont souvent évitables. D’après la littérature, ces erreurs humaines résultent souvent de compétences non-techniques telles que la communication, la collaboration et la gestion des situations difficiles. Pour prévenir les erreurs liées aux compétences non techniques, la formation par la simulation pourrait être une bonne approche. Ma thèse vise donc à étudier la contribution de la réalité virtuelle à la formation aux compétences non techniques dans le domaine de la santé : nous proposons de concevoir un bloc opératoire en réalité virtuelle ainsi que des scénarios pour permettre aux professionnel.le.s et étudiant.e.s des métiers de la santé de se familiariser avec des situations difficiles et de développer leurs compétences non-techniques. Après une mise en contexte sur le sujet des compétences non techniques, je vous présenterai le sujet de ma thèse, son déroulement prévisionnel et ferai un focus sur la première étude expérimentale prévue pour le mois d’Avril.
-===== Mardi 30 Juin 2020 15:00-16:00 =====
+**February 07, 2023 : Errors in procedural simulation. Improve their detection to better target feedback** \\
+  * **Speaker:** Matthieu Perrard\\
+  * **Sumarry:** Procedural simulation is at the heart of the pre-clinical training for dental students. The large number of learners forces the trainers to give late feedback from the final result of the exercises. The objective of this keynote is to propose a protocol for studying the gestures of students during procedural simulation sessions. The method will be based essentially on the video analysis of a standardized care sequence.
-==== "Paper presentation : Advancing Our Understandings of Healthcare Team Dynamics From the Simulation Room to the Operating Room: A Neurodynamic Perspective" ====
+**January 31, 2023 : No longer everything everywhere all at once: disambiguating voxel-based diktiometry in dementia and addiction** \\
-Présenté par : Thibaut Dognon
+  * **Speaker:** Alfonso Estudillo-Romero\\
+  * **Sumarry:** Our recent approach based on the voxel-based analysis (VBA) of the sensitivity maps of a simple CNN trained on diffusion MRI data has allowed us to calculate significance maps associated with some neurological diseases as for Parkinson’s disease and frontotemporal lobe dementia (FTLD) but preliminary results have also showed to be a promising tool in searching for patterns in addiction disorders as in cocaine use disorder (CUD) for example.Due to some extent of heterogeneity of the patients represented by the different clinical variants of the neurological diseases, we find it relevant to investigate the different patterns that each variant contributes to such significance maps. One of our hypotheses is that the biomarkers found by our previous approach is the result of a combination of more specific biomarkers that are associated with the different clinical variants of the disease. In this presentation we will show preliminary results of the biomarkers’ decomposition based on two well-known methods traditionally used for source separation problems: independent component analysis (ICA) and non-negative matrix factorization (NNM).
-"The initial models of team and team member dynamics using biometric data in healthcare will likely come from simulations. But how confident are we that the simulation-derived high-resolution dynamics will reflect those of teams working with live patients? We have developed neurodynamic models of a neurosurgery team while they performed a peroneal nerve decompression surgery on a patient to approach this question. The models were constructed from EEG-derived measures that provided second-by-second estimates of the neurodynamic responses of the team and team members to task uncertainty. The anesthesiologist and two neurosurgeons developed peaks, often coordinated, of elevated neurodynamic organization during the patient preparation and surgery which were similar to those seen during simulation training, and which occurred near important episodes of the patient preparation and surgery. As the analyses moved down the neurodynamic hierarchy, and the simulation and live patient neurodynamics occurring during the intubation procedure were compared at progressively smaller time scales, differences emerged across scalp locations and EEG frequencies. The most significant was the pronounced suppression of gamma rhythms detected by the frontal scalp sensors during the live patient intubation which was absent in simulation trials of the intubation procedure. These results indicate that while profiles of the second-by-second neurodynamics of teams were similar in both the simulation and live patient environments, a deeper analysis revealed differences in the EEG frequencies and scalp locations of the signals responsible for those team dynamics. As measures of individual and team performance become more micro-scale and dynamic, and simulations become extended into virtual environments, these results argue for the need for parallel studies in live environments to validate the dynamics of cognition being observed."
+**January 17, 2023 : Winter noon sharing planning** \\
+  * **Speaker:** John Baxter\\
-===== Lundi 22 Juin 2020 15:00-16:00 =====
-==== "Paper presentation : Optimization of targeting specific areas by optimization of medical image processing methods based on deep learning" ====
+===== 2022 =====
-Présenté par : Quoc-Anh Bui
+**December 13, 2022 : Learning surgery ergonomics** \\
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** Surgical procedures require many skills, which are technical and non-technical, both must be learned by surgeons to improve surgery quality. My thesis project is about the automated analysis of non-technical skills and more particularly posture and ergonomics to conclude the development of the pedagogical tool. This noonsharring presentation will be a brief state-of-the-art concerning sensor-based posture analysis and the place of ergonomics in the surgeons' learning. This work will allow us to compare and situate our study project with the final goal to write a review.
-"Transcranial Magnetic Stimulation treatment is a therapeutic technique that targets a specific area of the brain, in a non-invasive way. Individual positioning of the instruments for each patient improves the quality and effectiveness of the treatment. Therefore, improving the existing registration algorithm is necessary to improve the robustness, accuracy, reproducibility and preprocessing time of imaging data."
+**December 06, 2022 : SPARS Project: Sequential Pattern Analysis in Robotic Surgery** \\
+  * **Speaker:** Soline Galuret\\
+  * **Sumarry:** The objective is to propose data analysis methods to better understand surgery, a complex activity that depends on many factors, including patient and surgeon characteristics. Such complexity and variability explain why there is almost no detailed study of the surgical practice yet. The surgical procedure in the operating room is often considered as a whole and is technically described with few words. Analysis usually consists in comparing the impact of different surgical approaches or of different pre-operative clinical patient’s parameters on post-operative outcomes. In the SPARS project, we will rely on a combination of data and model-driven approaches to analyze and compare kinematics of whole surgical procedures acquired during robotic assisted hysterectomies. The studied methods will be applied and validated on a unique data set of more than 60 surgeries with kinematics, annotated videos and clinical parameters. We wish to demonstrate the clinical added value of the project by developing and evaluating a visualization software to visualize and understand differences in practice between populations.
-===== Jeudi 18 Juin 2020 15:00-16:00 =====
+**November 29, 2022 : synthesis of MER signals from the subthalamic nucleus** \\
+  * **Speaker:** Thibault Martin\\
-==== "Paper presentation : Person-Based Versus Generalized Impulsivity Disinhibition in Frontotemporal Dementia and Alzheimer Disease" ====
+**November 17, 2022 : Détermination de la position d'une caméra en utilisant les images des objets déformables** \\
-Présenté par : Delphine Tanguy
+  * **Speaker:** Yasser Derrar\\
+  * **Sumarry:** Nous présentons une nouvelle approche pour aligner de manière rigide une caméra prospective à la déformation d'un objet non rigide. Nous supposons avoir une trajectoire de caméra pré-planifiée de référence visualisant un objet non rigide. Notre objectif, est d'aligner cette trajectoire au temps d'exécution donné a priori uniquement sur le repère le plus pertinent. Notre méthode ne suppose aucun modèle a priori paramétrique ou non paramétrique sur la physique de la déformation. La méthode proposée est formalisée comme un problème de suivi intégré dans un cadre de contrôle optimal.
-"Background: While much disinhibition in dementia results from generalized impulsivity, in behavioral variant frontotemporal
+**November 08, 2022 : Deep Neural Network Architecture for Automated Soft Surgical Skills Evaluation Using Objective Structured Assessment of Technical Skills (OSATS) Criteria** \\
-dementia (bvFTD) disinhibition may also result from impaired social cognition. Objective: To deconstruct disinhibition and its
+  * **Speaker:** Malik Benmansour\\
-neural correlates in bvFTD vs. early-onset Alzheimer’s disease (eAD). Methods: Caregivers of 16 bvFTD and 21 matched-eAD
+  * **Sumarry:** Ma présentation portera sur une explication brève et concise de mon papier journal qui est en cours de révision. Il s’agit d’un travail d’établissement d’un système automatique (réseau de neurones artificiels dans mon cas) pour l’évaluation des compétences chirurgicales sur une échelle continue à partir de données cinématiques provenant du système chirurgical DaVinci. En effet, les méthodes d’évaluation classiques consistent à catégoriser les niveaux d’expertises des chirurgiens dans des classes discrètes (par ex. : novice, intermédiaire et expert) mais sont incapables de mettre en évidence les différences en compétences qui peuvent exister entre des chirurgiens ayant un même niveau d’expertise. Par conséquent, je propose dans cette contribution une nouvelle approche d’évaluation de compétences chirurgicales sur une échelle continue entre 1 et 5 et cela sur 6 critères chirurgicaux appelées OSATS qui permet de dépasser la restriction imposée par l’évaluation sur des catégories. L’architecture du réseau proposée est un CNN+BiLSTM qui a été entraîné avec des données cinématiques de la base de données publique JIGSAWS. Ces données représentent les mouvements des outils du robot DaVinci faits par des chirurgiens apprentis en effectuant trois tâches chirurgicales basiques : knot-tying, needle-passing et suturing. Enfin, lors de la phase de test, le réseau arrive à délivrer des prédictions proches des sorties désirées.
-patients completed the Frontal Systems Behavior Scale disinhibition items. The disinhibition items were further categorized into (1)
-‘‘person-based’’ subscale which predominantly associated with violating social propriety and personal boundary and (2) ‘‘generalized impulsivity’’
-subscale which included nonspecific impulsive acts. Subscale scores were correlated with grey matter volumes from
-tensor-based morphometry on magnetic resonance images. Results: In comparison to the eAD patients, the bvFTD patients
-developed greater person-based disinhibition (P < 0.001) but comparable generalized impulsivity. Severity of person-based disinhibition
-significantly correlated with the left anterior superior temporal sulcus (STS), and generalized-impulsivity correlated with the
-right orbitofrontal cortex (OFC) and the left anterior temporal lobe (aTL). Conclusions: Person-based disinhibition was predominant
-in bvFTD and correlated with the left STS. In both dementia, violations of social propriety and personal boundaries
-involved fronto-parieto-temporal network of Theory of Mind, whereas nonspecific disinhibition involved the OFC and aTL."
-===== Mardi 2 Juin 2020 15:00-16:00 =====
+**October 25, 2022 : Multimodal physiological sensor-based analysis of surgical non technical-skills in training environments: study presentation** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Surgical simulation has become an important part of the surgeon training program. Simulation is mostly performed autonomously and only receives feedback on evaluation measures based on outcomes that can be directly measured by the simulators: execution time, instrument collisions, workspace overlap, length of movements, etc. However, this information is not sufficiently informative and does not always reflect surgical expertise. To qualify the expertise, many scores exist, such as the ASSET score [1] or GOALS [2]. These scores aim at standardizing the evaluation of expertise thanks to a list of important points such as dexterity or safety. These scores are evaluated by experts who observe the learner. They are therefore subjective and time-consuming. It has been shown that kinematic data can be used to partially identify the GOALS score automatically [3]. However, the non-technical skills highlighted by these scores, such as autonomy or quality of the procedure, are not only related to the movement of the instruments. During this afternoon-sharing, I will present the objectives and first reflections of this new project
-==== "Assessing scrub nurses' non-technical skills in a virtual and collaborative environement" ====
+**October 18, 2022 : Impact of non-technical skills and environment in the operating room during caesarean-section on women’s birthing experience** \\
-Présenté par : Marie-Stéphanie Bracq
+  * **Speaker:** Maela Le Lous\\
+  * **Sumarry:** Emergency cesarean section is a traumatizing experience, which lead to a 10% rate of post traumatic stress disorder, mostly when performed in emergency (6). Although it is the most frequent intervention in the world, and it have a major impact of future health of children all over the world, little is known about soft skills during cesarean section. Interventions to create a positive perception of childbirth experience. The objective of this study is to assess the impact of light level, sound level, and motion level in the operating room during the different levels of emergency caesarean sections (green code, orange code and red code) and its impact on women’s birthing experience and prevalence of post-traumatic stress disorder.
-"This research is part of a multidisciplinary project to develop a virtual reality (VR) training environment in non-technical skills (NTS) for scrub nurses. The objective of this thesis was to provide the partners with the choice of NTS, to define training scenarios and to provide a first proof of concept on a targeted population.
+**October 11, 2022 : Errors of type or errors of degree? A Bayesian update** \\
-According to the literature and interviews with expert scrub nurses, the NTS selected for the scenarios are situation awareness (SA) and speaking up.
+  * **Speaker:** John Baxter\\
-Study 1, carried out with 13 scrub nurses and 16 non-experts, aims to assess the acceptability of the environment with the "instrumentation table" scenario (under VR helmet).
+  * **Sumarry:** Transcranial magnetic stimulation (TMS) is a non-invasive therapeutic procedure in which specific cortical brain regions are stimulated in order to disrupt abnormal neural behaviour. This procedure requires the annotation of a number of cortical point targets which is often performed by a human expert. Nevertheless, there is a large degree of variability between experts that cannot be described readily using the existing zero-mean uni-modal error model common in computer-assisted interventions. This is due to the error between experts arising from a difference of type rather than a difference of degree, that is, experts are not necessarily picking the same point with some error, but are picking fundamentally different points. At SPIE Medical Imaging, I presented a probabilistic model for errors of type which I then applied to a TMS target localisation task. Through maximum a posteriori optimisation, the best-fit model parameters could be inferred, which largely agreed with previous studies, but the model didn't permit for certain values, notably the uncertainty of these parameters, to be estimated. In this presentation, I will show an updated regularised model in which this is possible through Bayesian analysis, giving updated parameter estimates for our TMS dataset.
-Study 2, involving 18 scrub nursing students and 8 scrub nurses during an in-service course, aims to develop situation awareness, using the "virtual operating room of errors" scenario (under VR helmet). This scenario enables SA to be assessed and seems a suitable training tool for this NTS.
-Finally, Study 3, involving 33 scrub nursing students, aims to develop speaking up with a tablet scenario. Our results partially confirm the effect of status on the probability of speaking up and show an effect of status on the discomfort of speaking up.
-Each study involved numerous exchanges with the project's VR engineers and scrub nursing teachers in order to allow the construction of the environment and its future integration into the scrub nursing school pedagogy. Finally, for each study, specific assessment tools were used and simulation sessions were developed according to recommendations with briefing, simulation, debriefing (HAS, 2012)."
-===== Mardi 26 Mai 2020 15:00-16:00 =====
+**September 06, 2022 : Diffusion tensor imaging biomarkers for Parkinson’s disease symptomatology** \\
+  * **Speaker:** Alfonso Estudillo-Romero\\
+  * **Sumarry:** Voxel-based analysis is an invaluable tool for biomarker discovery in population neuroimaging. The traditional approach however is limited to local, linear biomarkers, determining if the linear correlation between the quantitative value of an image is correlated with the disease state at a single voxel. By analysing convolutional neural networks that directly predict clinical scores using a newly proposed voxel-based diktiometry, non-linear and non-local biomarkers can be visualised, leading to an additional tool for biomarker discovery. Our approach using diffusion tensor images to predict UPDRS3 and Hoehn & Yahr scores for Parkinson’s disease patients shows consistent and explainable results.
-==== "Paper presentation : Advancing Our Understandings of Healthcare Team Dynamics From the Simulation Room to the Operating Room: A Neurodynamic Perspective" ====
+**August 30, 2022 : Analyse de l'expertise chirurgicale basée sur l'acquisition de données cinématiques lors de chirurgies assistées par robot** \\
-Présenté par : Thibaut Dognon
+  * **Speaker:** Victor Jan\\
+  * **Sumarry:** La chirurgie assistée par télémanipulation est aujourd'hui présente dans de nombreux domaines de la chirurgie et utilisée dans beaucoup d'hôpitaux, comme c'est le cas par exemple avec l'hôpital de Pontchaillou à Rennes qui en possède deux. Le laboratoire MediCIS spécialisé dans l'évaluation et l'entraînement chirurgical travaille actuellement sur l'étude de l'expertise chirurgicale assistée par télémanipulation. J'ai eu la chance d'intégrer leur équipe durant quelques mois pour analyser séquentiellement des opérations chirurgicales d'hystérectomie. Grâce aux travaux en amont des chirurgiens de l'équipe, les vidéos de chaque opération sont annotées par phase et étapes. L'analyse s'effectuant sur les données cinématiques, la synchronisation des données vidéos avec les données cinématiques est essentielle et constitue la première partie du framework. Les annotations étant compressées avec des tampons de protocoles, il faut les décompresser et sélectionner les informations intéressantes. A partir de ces annotations et des données cinématiques synchronisées, on peut ensuite couper ces données en phase et étape pour l'analyse séquentielle. Rentre en jeu le software TRACAS qui permet le calcul de nouvelles variables moyennes plus faciles à interpréter qualitativement. Pour terminer cette analyse, et faciliter la lecture de ces résultats, on les affiche sous forme de boxplots puis on calcule le test de Mann & Whitney pour vérifier la significativité. On effectue également une analyse discriminante qui permet d'en ressortir les variables les plus discriminantes.
-"The initial models of team and team member dynamics using biometric data in healthcare will likely come from simulations. But how confident are we that the simulation-derived high-resolution dynamics will reflect those of teams working with live patients? We have developed neurodynamic models of a neurosurgery team while they performed a peroneal nerve decompression surgery on a patient to approach this question. The models were constructed from EEG-derived measures that provided second-by-second estimates of the neurodynamic responses of the team and team members to task uncertainty. The anesthesiologist and two neurosurgeons developed peaks, often coordinated, of elevated neurodynamic organization during the patient preparation and surgery which were similar to those seen during simulation training, and which occurred near important episodes of the patient preparation and surgery. As the analyses moved down the neurodynamic hierarchy, and the simulation and live patient neurodynamics occurring during the intubation procedure were compared at progressively smaller time scales, differences emerged across scalp locations and EEG frequencies. The most significant was the pronounced suppression of gamma rhythms detected by the frontal scalp sensors during the live patient intubation which was absent in simulation trials of the intubation procedure. These results indicate that while profiles of the second-by-second neurodynamics of teams were similar in both the simulation and live patient environments, a deeper analysis revealed differences in the EEG frequencies and scalp locations of the signals responsible for those team dynamics. As measures of individual and team performance become more micro-scale and dynamic, and simulations become extended into virtual environments, these results argue for the need for parallel studies in live environments to validate the dynamics of cognition being observed."
+**July 19, 2022 : Surgical Workflow Recognition on Total Knee Arthroplasties: Challenges and initial results** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** During my last noon sharing (in February), we discussed the challenges coming from the data to make a workflow recognition method for three types of arthroplasty surgeries. For this afternoon-sharing, I will briefly come back to these challenges and present the solutions chosen to solve them. Finally, I will present the initial results and the new challenges that I now encounter.
-===== Mardi 26 Mai 2020 15:00-16:00 =====
+**July 05, 2022 : Discussion autour d'une étude sur l'acceptabilité d'un logiciel de segmentation et d'editing segmentation** \\
+  * **Speaker:** John Baxter\\
-==== "Paper presentation : Connectivity predicts deep brain stimulation outcome in Parkinson Disease" ====
+**June 21, 2022 : Diffusion tensor imaging biomarkers for Parkinson’s disease symptomatology based on voxel-based diktiometry** \\
-Présenté par : Alfonso Estudillo
+  * **Speaker:** Alfonso Estudillo-Romero\\
-"Objective: The benefit of deep brain stimulation (DBS) for Parkinson disease (PD) may depend on connectivity between the stimulation site and other brain regions, but which regions and whether connectivity can predict outcome in patients remain unknown. Here, we identify the structural and functional connectivity profile of effective DBS to the subthalamic nucleus (STN) and test its ability to predict outcome in an independent cohort.
+**June 14, 2022 : Rapport des congrès CARS et RITS** \\
+  * **Speaker:** Tour de table\\
-Methods: A training dataset of 51 PD patients with STN DBS was combined with publicly available human connectome data (diffusion tractography and resting state functional connectivity) to identify connections reliably associated with clinical improvement (motor score of the Unified Parkinson Disease Rating Scale [UPDRS]). This connectivity profile was then used to predict outcome in an independent cohort of 44 patients from a different center.
+**May 17, 2022 : Le transfert de connaissances en éthologie pour la résolution de problèmes mathématiques** \\
+  * **Speaker:** Thibault Martin\\
-Results: In the training dataset, connectivity between the DBS electrode and a distributed network of brain regions correlated with clinical response including structural connectivity to supplementary motor area and functional anticorrelation to primary motor cortex (p < 0.001). This same connectivity profile predicted response in an independent patient cohort (p < 0.01). Structural and functional connectivity were independent predictors of clinical improvement (p < 0.001) and estimated response in individual patients with an average error of 15% UPDRS improvement. Results were similar using connectome data from normal subjects or a connectome age, sex, and disease matched to our DBS patients.
+**May 10, 2022 : Personalized Preoperative Planning for Hip Revision Surgery using 3D Modeling** \\
+  * **Speaker:** Alexandre Tronchot\\
+  * **Sumarry:** 130,000 new total hip replacements (THRs) are implanted annually in France, while approximately 20,000 older ones have to be replaced because of wear and loosening. For the past 10 years, the filling of bone loss (BL) with reusable metal blocks of various shapes and sizes has led to greater prosthetic survival. In case of acetabular protrusion or trans-acetabular fracture, a peripherally supported metal frame (“cage”) is used to reinforce the cup. Unlike allografts, all of these metallic materials have unchangeable mechanical properties and dispense with graft harvesting, preservation and sterilization protocols. But whatever the technique chosen, it is very difficult to anticipate preoperatively the exact modalities of these reconstructions despite the progress in imaging due to the superposition of the images of the skeleton and the prosthetic material unsealed but still in place before the revision. Thus, the location, shape, and dimensions of the BL and the dimensions of the revision acetabular component are difficult to anticipate. This forces surgeons to plan for many possibilities and to have a large quantity of material, some of which will not be used. Because they cannot order all the prosthetic materials for each revision, they may not even have the most appropriate material at the time of surgery. The hypothesis is that providing the surgeon with a 3D preoperative model of the iliac bone with the removal of the material in place leaving only the BL visible is: 1-realistic in terms of bone appearance, 2-compliant with the lesions, 3-facilitating reliable anticipation of the procedure through preoperative simulation. The objectives of the project are to demonstrate the validity of the 3D model in relation to preoperative images and intraoperative findings, and to compare the postural analyses of the operators obtained by RGBD video capture at the time of key operative sequences on the model and then intraoperatively. The expected results are in line with the general approach of 5P medicine: preventive, predictive, participative, personalized, pertinent: **(1)** Demonstrate the reliability of 3D printed models (face validity) during revisions of Paprosky type II and III acetabular loosening allowing the validation of a predictive and personalized preoperative model. **(2)** Open the way to preoperative training on 3D models in orthopaedic surgery in complex bone reconstructions and in the training of surgeons, making the model participatory and reducing the preoperative anxiety of surgical teams. **(3)** Provide a new model of operative anticipation, thus securing of interventions (better foreseen technical modalities), saving on operation time and reducing complications and costs linked to treatment failures, the clinical validation of which will make the model relevant.
-Interpretation: Effective STN DBS for PD is associated with a specific connectivity profile that can predict clinical outcome across independent cohorts. This prediction does not require specialized imaging in PD patients themselves."
+**May 03, 2022 : Présentation du la philosophie de l'imagerie médicale et introduction sur le congrès EPIMI** \\
+  * **Speaker:** John baxter\\
-===== Mardi 11 Mai 2020 15:00-16:00 =====
+**April 19, 2022 : Presentation of annotation software for segmentation of areas of interest** \\
+  * **Speaker:** Soline Galuret\\
+  * **Sumarry:** Soline requires your assistance for her internship project. To expand her dataset, she needs you to annotate videos by segmenting three zones of interest. Each participant will receive a unique set of data, as well as a shared set, to ensure that the annotations are consistent and comparable. She will provide a detailed presentation of the annotation software and task.
-==== "Paper presentation : Intraoperative Localization of STN During DBS Surgery Using a Data-Driven Model" ====
+**April 12, 2022 : Présentation CARS 2024** \\
-Présenté par : Thibault Martin
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** In the context of CARS congress we submit the master’s works concerning the surgeon’s posture detection. This project aims to detect body joints thanks to an human pose estimation algorithm, in our case OpenPose, directly on videos recorded during simulation training. The video dataset includes three expertise levels : novices, confirmed & experts and bases on arthroscopic simulation. Body joints coordinates contained some noisy data which was treated with the Savitzky Golay filter. To analyze the surgeon's movements, the picture of the workspace was split into 10*10 pixels squares and reported in a matrix. The frequency of presence of coordinates inside the square was visualized with a gray scale grid and was allowed to calculate the mobility score. This score was calculated for each expertise level, each articulation of interest (shoulders, elbows and wrists) and each exercise. Statistical analyses were done and highlighted some significant differences between expertise groups. In particular between novices or confirmed versus expert surgeons. The perspectives of this work are to calculate more metrics to distinguish the expertise level and to apply our method to more complex surgery tasks.
-"A new approach is presented for localizing the Subthalamic Nucleus (STN) during Deep  Brain Stimulation (DBS) surgery based on microelectrode recordings (MERs). DBS is an accepted treatment for individuals living with Parkinson’s Disease (PD). This surgery involves implantation of a permanent electrode inside the STN to deliver electrical current. Since the STN is a very small region inside the brain, accurate placement of an electrode is a challenging task for the surgical team. Prior to placement of the permanent electrode, microelectrode recordings of brain activity are used intraoperatively to localize the STN. The placement of the electrode and the success of the therapy depend on this location. In this paper,  an objective approach is implemented to help the surgical team in localizing the STN. This is achieved by processing the MER signals and extracting features during the surgery to be used in a Machine Learning (ML) algorithm for defining the neurophysiological borders of the STN. For this purpose, a new classification approach is proposed with the goal of detecting both the dorsal and the ventral borders of the STN during the surgical procedure. Results collected from 100 PD patients in this study, show that by calculating and extracting wavelet transformation features from MER signals and using a data-driven computational deep neural network model, it is possible to detect the borders of the STN with an accuracy of 92%. The proposed method can be implemented in real-time during the surgery to model the neurophysiological nonlinearity along the path of the electrode trajectory during insertion."
+**March 22, 2022 : An ongoing review on machine learning-based approaches to diffusion MRI in epilepsy** \\
+  * **Speaker:** Alfonso Estudillo-Romero\\
+  * **Sumarry:** Epilepsy is a neurological disorder characterized by recurrent and disabling seizures associated with abnormal activities in the brain. Given the heterogeneous types of epilepsy we need to first focus on the clinical aspects of each epilepsy type to propose a particular application. The most challenging applications include patient-specific characterization of the disorder for proper patient-specific medication or therapy. Based on the characterization of the motion of water, the diffusion tensor imaging can provide data on the structural integrity of brain tissues and quantitative measures of diffusion and fractional anisotropy. With the preferred orientation of the diffusion of water in the brain we can visualize white matter pathways and infer its underlying connections. Changes on the delimited pathways and its underlying networks may be due to specific epilepsy syndromes. We summarize some of the machine learning based approaches using diffusion MRI in epilepsy.
-===== Mardi 5 Mai 2020 15:00-16:00 =====
+**March 15, 2022 : Design d’une approche Data-Driven pour la simulation de signaux électrophysiologiques** \\
+  * **Speaker:** Thibault Martin\\
+  * **Sumarry:** Les travaux de recherche sur la génération de données rendent comptent d’un essor de nouvelles méthodologies Data-driven pendant la dernière décennie. Néanmoins, ces méthodes portent essentiellement sur la génération d’images. La génération de données audio brute reste un challenge en recherche de part la complexité de modélisation des dépendances à court et long-terme sur de longues séries temporelles. Ce Noon Sharing sera dédié à la présentation de récents modèles génératifs de Deep Learning adaptés à des séries Toupirelles ayant une nature proche de celle des signaux électrophysiologiques. Cette séance aura également pour objectif de proposer un protocole adapté au projet de production de signaux synthétiques, en vue de fournir un support didactique de simulation clinique.
-==== "Paper presentation : Deep Double Descent: Where Bigger Models and More Data Hurt" ====
+**March 08, 2022 : La bipolarité : un trouble magnétique? D'une catégorie cohérente à des causalités multiples** \\
-Présenté par : John Baxter
+  * **Speaker:** Enora Giffard\\
-"We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. Moreover, we show that double descent occurs not just as a function of model size, but also as a function of the number of training epochs. We unify the above phenomena by defining a new complexity measure we call the effective model complexity and conjecture a generalized double descent with respect to this measure. Furthermore, our notion of model complexity allows us to identify certain regimes where increasing (even quadrupling) the number of train samples actually hurts test performance."
+**February 15, 2022 : Arthroplasties workflow recognition from two video streams** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** For this noon-sharing, I will briefly present the work done on the two first years of the "CASRAA: Context Awareness and Surgical Process Model for Robotic Assisted Arthroplasty" project in collaboration with Stryker and Innsbruck hospital. Then I will make a focus on the next step: the automatic workflow recognition on Arthroplasty surgeries. I would present the challenges of the data and initial ideas to manage it. I hope you could help with the reflection with your questions and feedbacks
-===== Mardi 5 Mai 2020 15:00-16:00 =====
+**February 08, 2022 : Errors of type or errors of degree? Cortical point targeting in transcranial magnetic stimulation** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Répétition présentation SPIE 2022
-==== "Paper presentation : Development of an Interactive Dashboard to Analyze Cognitive Workload of Surgical Teams During Complex Procedural Care" ====
+**February 01, 2022 : Génération de vocalisations de corbeau freux à partir d’un auto-encodeur interpolant avec entraînement antagoniste et reconstruction du signal sonore** \\
-Présenté par : Arnaud Huaulmé
+  * **Speaker:** Soline Galuret\\
-"In the surgical setting, team members constantly deal with a high-demand operative environment that requires simultaneously processing a large amount of information. In certain situations, high demands imposed by surgical tasks and other sources may exceed team member's cognitive capacity, leading to cognitive overload which may place patient safety at risk. In the present study, we describe a novel approach to integrate an objective measure of team member's cognitive load with procedural, behavioral and contextual data from real-life cardiac surgeries. We used heart rate variability analysis, capturing data simultaneously from multiple team members (surgeon, anesthesiologist and perfusionist) in a real-time and unobtrusive manner. Using audio-video recordings, behavioral coding and a hierarchical surgical process model, we integrated multiple data sources to create an interactive surgical dashboard, enabling the analysis of the cognitive load imposed by specific steps, substeps and/or tasks. The described approach enables us to detect cognitive load fluctuations over time, under specific conditions (e.g., emergencies, teaching) and in situations that are prone to errors. This in-depth understanding of the relationship between cognitive load, task demands and error occurrence is essential for the development of cognitive support systems to recognize and mitigate errors during complex surgical care in the operating room."
+**January 14, 2022 : Enregistrement des données climatiques : Earth blackbox** \\
+  * **Speaker:** Tiphaine Casy\\
+  * **Sumarry:** Basé sur le modèle des boîtes noires aériennes permettant de comprendre les causes d'un crash, des chercheurs et une compagnie de communication Australienne ont imaginé une "Earth black box" (ou "Boîte noire de la Terre"). Le rôle de cette dernière serait l'enregistrement quotidiens des mouvements climatiques (fonte des glaces, augmentation du climat,...) des dépenses militaires, de la croissance démographique et des contenus de différents médias. Sa conception permettrait un stockage de 30 à 50 ans dans le but d'informer les générations futures sur les actions ou non-actions orientant la Terre sur son déclin. Cette idée est venue suite à l'observation de la progression continue du réchauffement climatique et de ses impacts écologiques, économiques et humains. Les chiffres actuels correspondent à ceux prédis en 1972 dans une étude menée par le MIT ("The limits of growth") et tendent vers un déclin total de la Terre vers la fin du siècle s'il n'y a aucune modification sociétale.
-===== Mardi 28 Avril 2020 15:00-16:00 =====
-==== "Paper presentation : Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance" ====
+===== 2021 =====
-Présenté par : Julien Berthelemy
-"Dynamical systems can generate movement trajectories that are robust against perturbations. This article presents an improved modification of the original dynamic movement primitive (DMP) framework by Ijspeert et al [1], [2]. The new equations can generalize movements to new targets without singularities and large accelerations. Furthermore, the new equations can represent a movement in 3D task space without depending on the choice of coordinate system (invariance under invertible affine transformations). Our modified DMP is motivated from biological data (spinal-cord stimulation in frogs) and human behavioral experiments. We further extend the formalism to obstacle avoidance by exploiting the robustness against perturbations: an additional term is added to the differential equations to make the robot steer around an obstacle. This additional term empirically describes human obstacle avoidance. We demonstrate the feasibility of our approach using the Sarcos Slave robot arm: after learning a single placing movement, the robot placed a cup between two arbitrarily given positions and avoided approaching obstacles."
+**December 21, 2021 : Présentation du projet CUFFSIM** \\
+  * **Speaker:** Nicolas Vallée  \\
-===== Mardi 14 Avril 2020 15:00-16:00 =====
+**December 14, 2021 : Le stress post traumatique** \\
+  * **Speaker:** Enora Giffard  \\
-==== "Academic background and PhD project" ====
+**November 30, 2021 : nan** \\
-Présenté par : Delphine Tanguy
+  * **Speaker:** Invité: Tamás Haidegger\\
+  * **Sumarry:** For the Noon sharing Tamás Haidegger, associate professor at Óbuda University, serving as the director of the University Research and Innovation Center (EKIK), and as the technical lead of medical robotics research at the Antal Bejczy Center for Intelligent Robotics. His main field of research is on medical technologies, control/teleoperation of surgical robots, image-guided therapy and digital health technologies.
-"A quick summary of my academic background followed by a presentation of my thesis project: the neural basis of disinhibition in neurodegenerative diseases. This will be a first introduction to my PhD project and a description of the protocols used, without any results presentation."
+**November 23, 2021 : PETRAW Challenge results** \\
+  * **Speaker:** Arnaud Huaulmé\\
-===== Mardi 7 Avril 2020 15:00-16:00 =====
+**November 02, 2021 : Voxel-Based Diktiometry - Merging convolutional neural networks with voxel-based analysis for characterization of diffusion MRI for Parkinson’s disease.** \\
+  * **Speaker:** Alfonso Estudillo-Romero  \\
-==== "Overview of my past projects" ====
+**October 19, 2021 : Répétition de soutenance de stage  (Michaël) & répétation de sounteance de thèse (Delphine)** \\
-Présenté par : Alfonso Estudillo
+  * **Speaker:** Michaël Nguyen  & Delphine Tanguy \\
-"In this meeting I am going to introduce a bit of myself, where I came from and what I did in my master and PhD theses. I am going to also show some projects I have involved with and finally the current project at MediCIS."
+**October 12, 2021 : MENISIM, Simulation VR pour apprendre les bases de l'arthroscopie : Retour sur les travaux de l'année écoulée** \\
+  * **Speaker:** Alexandre Tronchot  \\
+  * **Sumarry:** Voilà 1 an que le projet MENISIM a démarré (projet majeur de ma thèse de sciences). L'objectif de ce Noon Sharing sera de vous faire un rappel sur l'intérêt de ce travail dans la formation pratique à l'arthroscopie des chirurgiens orthopédistes, une description de la méthodologie employée, et un retour sur les premiers résultats. Je conclurais cette présentation par les perspectives du projet, et une brève explication du projet de master 2 de Nicolas qu'il présentera de façon plus détaillée en fin d'année.
-===== Vendredi 6 Mars 2020 13:00-14:00 =====
+**October 05, 2021 : Les représentations sociales du changement climatique et des actions pro-environnementales du Plateau des Petites roches** \\
+  * **Speaker:** Marie Le Duff  \\
-==== "History of Medecine, Study of medical and surgical knowledge and practices over time" ====
+**September 14, 2021 : Répétition de soutenance de Master : "Outils d'analyse d'une chirurgie : Hystérectomie robot-assitée** \\
-Présenté par : Alicia Diot
+  * **Speaker:** Sonia Guérin\\
-"The History of Medicine is the study of medical and surgical knowledge and practices over time.
+**September 07, 2021 : Présentation de l'expérience IHM (interaction homme-machine) sur un outil de segmentation du STN par l'apprentissage automatique** \\
-Thanks to the discoveries of traces of ancient medical knowledge, we understand that medical practice has always existed, the fight against pain and infirmity is as old as Humanity. What has evolved over the centuries are the means used in this fight, from magic to modern scanners, from shamans to specialized surgeons ...
+  * **Speaker:** John Baxter  \\
-Medicine is a discipline at the crossroads between Art and Science. From the origin of civilizations, it has been considered as an art, in the measure of intuition, empiricism, psychology ...
-Over time and with progress, it has become a science, based on the understanding of the human and its pathologies, on the identification of therapeutics, and the discovery of new techniques.
-Thus, while the art of healing is as old as mankind, Medicine as we know it today only dates back to the beginning of the 19th century. Since then, progress has continued at an impressive speed that keeps accelerating.
-It therefore seems difficult to retrace the evolution of Medicine in an exhaustive way, however, I will outline the main stages and dominant discoveries that have given rise to today’s medicine.
-It is important to understand that the division into chronological periods that I use in this presentation remains very artificial, the evolutions are actually very intertwined. Likewise, the great names that I cite as having largely contributed to the evolution of Medicine, are ultimately only a tiny part of the crowd that has participated in this evolution."
-===== Mardi 11 Fevrier 2020 13:00-14:00 =====
+**August 31, 2021 : Répétition de soutenance de stage de fin d'étude  ** \\
+  * **Speaker:** Enora Giffard\\
-==== "Topology-Aware Activation Layer for Neural Network Image Segmentation" ====
+**June 15, 2021 : CARS2021 - Adapting the Listening Time for Micro-Electrode Recordings in Deep Brain Stimulation Interventions** \\
-Présenté par : John Baxter
+  * **Speaker:** Thibault Martin\\
+  * **Sumarry:** Deep Brain Stimulation (DBS) is a common treatment for a variety of neurological disorders which involves the precise placement of electrodes at particular subcortical locations such as the subthalamic nucleus. This placement is often guided by auditory analysis of micro-electrode recordings (MERs) which informs the clinical team as to the anatomic region in which the electrode is currently positioned. Recent automation attempts have lacked flexibility in terms of the amount of signal recorded, not allowing them to collect more signal when higher certainty is needed or less when the anatomy is unambiguous. Therefore, we have addressed this problem by evaluating a simple algorithm that allows for MER signal collection to terminate once the underlying model has sufficient confidence. We have parameterized this approach and explored its performance using three underlying models composed of one neural network and two Bayesian extensions of said network. Our results shown that one particular configuration, a Bayesian model of the underlying network's certainty, outperforms the others and is relatively insensitive to parameterization. Further investigation shows that this model also allows for signals to be classified earlier without increasing the error rate. This work presents a simple algorithm that records the confidence of an underlying neural network, thus allowing for MER data collection to be terminated early when sufficient confidence is reached. This has the potential to improve the efficiency of DBS electrode implantation by reducing the time required to identify anatomical structures using MERs
-"One of the recent developments in deep learning is the ability to train extremely deep residual neural networks, knowing that each residual block produces only marginal changes to the data. The accumulation of these changes result in the network's improved performance, analogous to a complex but trainable iterative algorithm. This intuition can be merged with the underlying theory of probabilistic graphical models in which these iterative algorithms are common and share the underlying probabilistic and information theoretic basis as deep learning. Prior models have been proposed with limitations on the number of iterations allowed in the solution algorithm due to the linear memory growth during the training process. This paper presents a structured activation layer which implements a conditional random field along with an arbitrary iteration message-passing marginal probability estimation algorithm which requires constant, rather than linear, memory with respect to the number of iterations. In this activation layer, the segmentation labels can be specified hierarchically, incorporating a level of abstract structure and some basic geometrical knowledge directly and easily into the network. Thus, this layer allows for the separation of abstract knowledge brought in by the network designer (in the form of the hierarchical structure) from probabilistic priors learned by the neural network. Preliminary results comparing this activation function to softmax and a similar non-hierarchical activation function indicate that it significantly improves performance in segmentation problems."
+**June 08, 2021 : Robot-assisted laparoscopic hysterectomy: experts vs juniors ** \\
+  * **Speaker:** Sonia Guérin\\
-===== Mardi 11 Fevrier 2020 13:00-14:00 =====
+**June 01, 2021 : Study of anatomical and clinical correlation in tractography after deep brain stimulation of the anterior nucleus of the thalamus (ANT) for focal, inoperable and drug resistant epilepsy** \\
+  * **Speaker:** Mathilde Gaudian\\
-==== "Localisation of the Subthalamic Nucleus in MRI via Convolution Neural Networks for Deep Brain Stimulation Planning" ====
+**May 25, 2021 : Présentation des résultats du stage ** \\
-Présenté par : John Baxter
+  * **Speaker:** Tiphaine Casy\\
-"Deep brain stimulation (DBS) is an interventional treatment for Parkinson's disease in which electrodes are placed into specific locations in the basal ganglia to alleviate symptoms such as tremor and dyskinesia. Due to the small size and low contrast of specific targets of interest, such as the subthalamic nucleus (STN), localisation of these structures from pre-operative MRI is of great value. These localisation approaches are often atlas-based, using registration algorithms to align patient images with a prior annotated atlas. However, these methods require a large amount of time, especially for correctly estimating deformation fields, or are prone to error for smaller structures such as the STN. This paper investigates two deep learning frameworks for the localisation of the stn from T1- and T2-weighted MRI using convolutional neural networks which estimate its centroid. These methods are compared against an atlas-based segmentation using the ParkMedAtlis v3 atlas, showing an improvement in localisation error in the range of ~0.5-1.3 mm with a reduction of orders of magnitude of computation time. This method of STN localisation will allow us in future to automatically identify the STN for DBS surgical planning as well as define a greatly reduced region-of-interest for more accurate segmentation of the STN."
+**May 18, 2021 : REPEAT - Simulation par Réalité Virtuelle : utilisation et apport dans l'apprentissage de compétences non techniques dans la formation de l'interne en neurochirurgie ** \\
+  * **Speaker:** Julien Tinois\\
-===== Mardi 28 Janvier 2020 13:00-14:00 =====
+**May 11, 2021 : Multimodal investigation of epileptic network, insight from electrophysiology and hemodynamic processes ** \\
+  * **Speaker:** Christophe Grova (PhD, Associate Professor, Physics Dpt, Concordia University  and  Adjunct Professor in Biomedical Engineering, and Neurology and Neurosurgery Dpt at McGill University)\\
-==== "Clinical and technological study of the spine biomechanics, scoliosis-oriented" ====
+**April 20, 2021 : Le numérique responsable** \\
-Présenté par : Kevin Le Mut
+  * **Speaker:** Pierre Jannin\\
-"Scoliosis is the largest three-dimensional deformation in the human body. It causes many health issues and there is a lack of data to correct them properly. Surgeons can only use their experience to operate. The role of biomechanics and finite element simulations is to provide more data and to analyze the constraints within the spine."
+**April 06, 2021 : Bénéfice de l'état de flow sur l'efficacité des distractions dans la prise en charge de l’anxiété préopératoire en anesthésie pédiatrique** \\
+  * **Speaker:** Camille Tordet\\
+  * **Sumarry:** Les méthodes de distraction (jouet, dessin animé, jeu vidéo) ont été évaluées comme efficace dans la prise en charge de l’anxiété préopératoire des enfants. Les activités distractrices détournent l’attention des enfants des indices menaçants de la situation vers des activités et des pensées plus agréables. Toutefois, la variabilité d’efficacité de cette stratégie s’avère peu étudiée. En effet, si le bénéfice de la méthode de distraction s’explique par le transfert des ressources attentionnelles de la situation anxiogène vers l’activité distractrice, alors on devrait observer une variabilité d’efficacité selon le degré de ressources attentionnelles alloué sur l’activité. Ce travail cherche à analyser comment l’état de flow (état de concentration et d'absorption intense) peut fournir des explications, dans le but d’améliorer les distractions actuellement utilisées. Cette présentation abordera le contexte puis l’étude que nous avons menée au CHU de Rennes Sud, afin d’apporter des éléments de réponse à ces questions."
+**March 30, 2021 : Brain correlates of behavioural disinhibition in behavioural variant frontotemporal dementia** \\
+  * **Speaker:** Delphine Tanguy\\
+  * **Sumarry:** Disinhibition is a core symptom in neurodegenerative diseases, in particular in fronto-temporal dementia (FTD), and a major cause of stress for caregivers. However, the concept of this symptom is hard to disentangle: while a distinction between behavioural and cognitive disinhibition is common, an operational definition of behavioural disinhibition remains unclear. Therefore, available assessments of these behavioural disorders are imprecise and the corresponding neuroanatomical correlates are non-univocal.Thus, we aimed to characterise the anatomical networks underlying different subtypes of behavioural disinhibition. For this purpose, we used an original semi-ecological task assessing two specific dimensions of behavioural disinhibition, such as compulsivity and social disinhibition, in 17 behavioural variant of FTD patients and 18 healthy controls, associated with classic neuropsychological tests and brain imaging (voxel-based morphometry for the grey matter, tractography for the white matter). Compulsivity correlated with right temporal regions atrophy and with alterations of the bilateral cingulum and uncinate fasciculus, the right inferior longitudinal fasciculus and the right arcuate fasciculus. Social disinhibition was associated to huge bilateral frontal atrophy and impairments in the cingulum, the forceps minor and the left uncinate fasciculus. By combining ecological behavioural analyses with neuroanatomy, we identified two subtypes of behavioural disinhibition associated with differential neural networks
-===== Mardi 21 Janvier 2020 13:00-14:00 =====
+**February 23, 2021 : Automatic Cortical Target Point Localisation in MRI for Transcranial Magnetic Stimulation via a Multi-Resolution Convolutional Neural Network ** \\
+  * **Speaker:** John Baxter  \\
+  * **Sumarry:** Transcranial Magnetic Stimulation (TMS) is a growing therapy for a variety of psychiatric and neurological disorders that arise from or are modulated by cortical regions of the brain represented by singular 3D target points. These target points are often determined manually with assistance from a pre-operative T1-weighted MRI, although there is growing interest in automatic target point localisation using an atlas. However, both approaches can be time-consuming which has an effect on the clinical workflow and the latter does not take into account patient variability such as the varying number of cortical gyri where these targets are located. This paper proposes a multi-resolution convolutional neural network for point localisation in MR images for a priori defined points in increasingly finely resolved versions of the input image. This approach is both fast and highly memory efficient, allowing it to run in high-throughput centres, and has the capability of distinguishing between patients with high levels of anatomical variability. Preliminary experiments have found the accuracy of this network to be 7.26+5.30 mm, compared to 9.39+4.63 mm for deformable registration and 6.94+5.10 mm for a human expert. The human-level performance of this network indicates that it can improve TMS planning by automatically localising target points in seconds, avoiding more time-consuming registration or manual point localisation processes.
-==== "Convolutional Neural Network for Localizing the Subthalamic Nucleus Using One Second Micro-electrode Recordings" ====
+**February 16, 2021 : PETRAW: PEg TRAnsfer Workflow recognition by different modalities ** \\
-Présenté par : Maxime Peralta
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Automatic and online recognition of surgical workflows is mandatory to bring computer-assisted surgery (CAS) applications inside the operating room. According to the type of surgery, different modalities could be used for workflow recognition. In the case of robotic-assisted surgeries and virtual reality training sessions, video and kinematic data are easily available. However, even if these modalities are available, numerous methods on state of art only focus on one of them. Last year we submitted the MISAW sub-challenge as part of EndoVis at MICCAI2020 (challenge description and results available at https://www.synapse.org/MISAW, paper under writing), offering to participant to combine both modalities for the workflow recognition. To the best of our knowledge, there are very few studies about the added value to combine multiple modalities. Whereas, some study as demonstrate that the addition of external information improve the recognition, as the presence of tools. PETRAW is a sub-challenge of ENDOVIS 2021 currently on minor revision for MICCAI2021. PETRAW focuses on the comparison of 3 modalities (video, kinematic, and segmentation) and their combination on surgical workflow recognition. On this noon sharing, I will present the challenge design and probably partial results."
-"Micro-electrode recording (MER) is a powerful way of localizing target structures during neurosurgical procedures such as the implantation of deep brain stimulation electrodes which is a common treatment for Parkinson's disease and other neurological disorders. Although allowing better clinical results than guiding only with per-operative imaging, MER is not unanimously used in clinic, notably because of its long duration which can lead to complications during the operation, and because it requries a high degree of expertise.
+**February 09, 2021 : Preliminary results on the characterization of PD from DT images on the PPMI dataset by means of CNNs** \\
-Different approaches towards automating MER analysis and structure localization have been proposed on the last decade, mainly focused on feature engineering. While the accuracies obtained are good in certain configurations, one issue with handcrafted features is that they do not necessarily capture more subtle differences in MER that are detected by expert neurophysiologists by ear. In this presentation, i'll show you a deep learning based pipeline for subthalamic nucleus (STN) localization with micro-electrode recordings which is motivated by the human auditory system. The proposed Convolutional Neural Network (CNN) shows improved accuracy over two comparative networks for locating the STN from one second MERs."
+  * **Speaker:** Alfonso Estudillo-Romero  \\
+  * **Sumarry:** We present our preliminary results on the analysis of diffusion tensor images (DTI) by means of a Convolutional Neural Network (CNN) to classify Parkinsonian patients (PD) and healthy controls (HC) from brain images.  An analysis of the whole population registered in a common space is proposed to compute some of the classical anisotropy measures in a voxel-based approach. Moreover, we retrieved the back-propagated gradients of these images through the CNN to understand how sensitive the CNN is to some anisotropy measures at some particular regions.
-===== Mardi 7 janvier 2020 13:00-14:00 =====
+**February 02, 2021 : Extending Deep Neural Networks with Bayesian Inference and Recurrent Layers for Localizing the Subthalamic Nucleus from Micro-Electrode Recordings** \\
+  * **Speaker:** Thibault Martin\\
+  * **Sumarry:** Deep brain stimulation (DBS) is an interventional treatment for Parkinson's disease which involves the precise positioning of stimulation electrodes within particular subcortical anatomy. Although originally identified via imaging, additional inter-operative guidance is necessary to localize the target anatomy. Analysis of Micro-Electrode Recordings (MERs) allows for a trained neurophysiologist to infer the underlying anatomy at a particular electrode position using human audition, although it is subjective and requires a high degree of expertise. This project aims to develop and validate a deep neural network to assist in MER analysis during DBS which can use arbitrary length MERs while providing feedback to the neurophysiologist as to the model's certainty. We evaluate six different deep learning based classifiers which can use arbitrary length MERs for Sub-Thalamic Nucleus (STN) segmentation, finding a particular Baysian network to perform the best. With a view to providing decision support, the use of Bayesian inference has also made it possible to interpret the level of confidence in the predictions underlying the predictive model. This work represents a step forward in integrating automated analysis of MERs into the DBS surgical workflow by automatically finding and exploiting MER in a data-driven predictive model.
-==== "Kinematic data analysis for skill assessment in surgery: a review" ====
+**January 05, 2021 : Place de l’Apprentissage de la Chirurgie Arthroscopique utilisant la Simulation en Réalité Virtuelle (VR) à propos d’un Geste : la Méniscectomie - MENISIM-VR** \\
-Présenté par : Julien Berthelemy
+  * **Speaker:** Alexandre Tronchot\\
+  * **Sumarry:** Les dernières années ont été marquées par d'importantes avancées dans la formation initiale des jeunes chirurgiens avec du temps alloué supplémentaire et de nouveaux outils pédagogiques. Toutefois, le quotidien reste essentiellement occupé par le temps de service. Paradoxalement, les internes vont être mis en responsabilité plus vite avec un temps passé à l'hôpital plus court. La formation initiale doit donc à la fois assurer sa mutation et rester efficiente en trouvant des compléments et alternatives au traditionnel compagnonnage. La simulation est l'un des outils proposés pour cela, et elle a déjà fait ses preuves dans le domaine comportemental. Son évolution vers la réalité virtuelle (VR) est maintenant proposée pour la formation procédurale car elle offre un outil à la frontière entre réalités théorique et pratique et, surtout, inlassablement reproductible. La chirurgie arthroscopique est particulièrement adaptée à cette simulation VR du fait de son retour visuel per-opératoire sur écran 2D. Toutefois, et bien qu'il y ait de plus en plus d'articles scientifiques parlant de l'intérêt de la simulation VR en chirurgie arthroscopique, peu rapportent sa validité lors de la transposition des performances du simulateur vers le patient réel. Montrer que l'étudiant en progressant sur simulateur devient également performant au bloc opératoire serait une avancée considérable dans la formation médicale du troisième cycle, correspondant parfaitement aux demandes des Ministères de la Santé et de l'Enseignement Supérieur et la Recherche à la fois en termes de sécurité patient ("Jamais la première fois sur le patient"), mais aussi de sécurité du praticien et d'enjeux économiques de formation.
-===== Mardi 22 Octobre 2019 13:00-14:00 =====
-==== "Elephants in the Room:  How should we analyse trainee performance on simulator-based scenarios?" ====
+===== 2020 =====
-Présenté par : Roy Eagleson
+**December 08, 2020 : Hystérectomie : indications, modalités et apports de la chirurgie robot assistée.** \\
+  * **Speaker:** Sonia Guerin\\
+  * **Sumarry:** Hysterectomy is the most commonly performed gynecological procedure in high income countries. Eight-seven percent of indications are benign diseases. Several surgical approaches are possible, each with its own advantages and disadvantages. With the arrival of the surgical robot, it is now possible for us to study precisely the gestures performed by the surgeon thanks to kinematics and video data analysis. Initially, we will look at the indications, approaches and complications of hysterectomy before discussing the contribution of kinematic and video data in general surgery and in hysterectomy in particular
-===== Mardi 08 Octobre 2019 13:00-14:00 =====
+**December 01, 2020 : A semantic database for integrated management of image and dosimetric data in low radiation dose research in medical imaging** \\
+  * **Speaker:** Bernard Gibaud\\
+  * **Sumarry:** Medical ionizing radiation procedures and especially medical imaging are a non negligible source of exposure to patients. Whereas the biological effects of high absorbed doses are relatively well known, the effects of low absorbed doses are still debated. This work presents the development of a computer platform called Image and Radiation Dose BioBank (IRDBB) to manage research data produced in the context of the MEDIRAD project, a European project focusing on research on low doses in the context of medical procedures. More precisely, the paper describes a semantic database linking dosimetric data (such as absorbed doses to organs) to the images corresponding to X-rays exposure (such as CT images) or scintigraphic images (such as SPECT or PET images) that allow measuring the distribution of a radiopharmaceutical. The main contributions of this work are: 1) the implementation of the semantic database of the IRDBB system and 2) an ontology called OntoMEDIRAD covering the domain of discourse involved in MEDIRAD research data, especially many concepts from the DICOM standard modelled according to a realist approach.
-==== "What will happen to you if you go in medical device industry" ====
+**November 10, 2020 : Flexible recurrent neural network for Audio-Visual sequence analysis** \\
-Présenté par : Ehouarn Maguet
+  * **Speaker:** Tsiry Mayet\\
+  * **Sumarry:** Deep learning models are now brought closer to the user rather than running in a distant cloud, helping to reduce latency, network congestion, and improving data security and privacy. However, smartphones and user devices impose additional constraints such as limited computation or energy. Handling these constraints has become an active research topic. User devices can also host multiple processes running at the same time and starting or stopping abruptly, modifying the constraints affecting the processes. Few works have considered models that can be modified at run time to adapt to an evolving computational limit.
-"I will share with you some part of the daily life of a software engineer in a medical device industry.
+**October 20, 2020 : Data driven methods to support decision making in Deep Brain Stimulation for Parkinson’s Disease** \\
-I will talk about medical standard (and try not to be boring), audit, impact of software and hardware on regulation, a resolution bug example, and some anecdotes."
+  * **Speaker:** Maxime Peralta \\
-===== Mardi 01 Octobre 2019 13:00-14:00 =====
+**October 13, 2020 : MISAW - Part of the Endoscopic Vision Challenge** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Automatic and online recognition of surgical workflows is mandatory to bring computer-assisted surgery (CAS) applications inside the operating room. According to the type of surgery, different modalities could be used for workflow recognition. In the case where the addition of multiple sensors is not possible, the information available for manual surgery is generally restricted to video-only. In the case of robotic-assisted surgery, kinematic information is also available. It is expected that multimodal data would make easier automatic recognition methods. The “MIcro-Surgical Anastomose Workflow recognition” (MISAW) sub-challenge provides a unique dataset for online automatic recognition of surgical workflow by using both kinematic and stereoscopic video information on a micro-anastomosis training task. Participants are challenged to recognize online surgical workflow at different granularity levels (phases, steps, and activities) by taking advantage of both modalities available. Participants can submit results for the recognition of one or several granularity levels. In the case of several granularities, participants are encouraged (but not required) to submit the result of a multi-granularity workflow recognition, i.e. recognize different granularity levels thanks to a unique model.
-==== "Cognitive Oriented Design and Assessment of Augmented Reality in Medicine" ====
+**September 22, 2020 : Characterisation of three clinical-neurological subtypes of the bvFTD based on inhibition deficit symptoms assessed through an ecological approach** \\
-Présenté par : Pierre Jannin
+  * **Speaker:** Delphine Tanguy\\
-"Mixed and Augmented Reality (AR) is a technology that aims to augment the perception of reality by adding computer-generated information. Such technology has been applied for medical procedures (especially surgery) the past 20 years to help physicians understand and perform procedures, as well as for training. However, as outlined in different review papers, AR has not yet reached its full potential usefulness and implementation in the medical workflow.
+**September 15, 2020 : Review of my work** \\
-Many reasons for this have been expressed; one is that the AR system design approach is mainly technology driven, resulting in the need to develop relevant and clinically valuable AR applications. Another reason is the lack of relevant assessments of proposed AR systems to validate their benefits in all aspects of medical care. In this presentation, I will suggest a cognitive-oriented approach for both optimal design and assessment of AR systems. This approach is based on two main statements: (1) ensuring proper definition and modeling of medical objective(s) and (2) considering understanding as the main motivation for AR."
+  * **Speaker:** Kevin Le Mut\\
+  * **Sumarry:** During 1 year of contract I carried out various works at MEDICIS. My main objective was the annotation of hysterectomy videos but I also participated in the annotations of the MISAW project and started to develop an application. In addition to this, various tasks were added to complete my work such as annotation protocol build on SurgePlan. The year 2020 was full of hazards that slowed down the progress of the work.
-===== Mardi 17 Septembre 2019 13:00-14:00 =====
+**September 09, 2020 : Shared meeting with the VASST team** \\
+  * **Speaker:** Thibaut Dognon\\
-==== "Augmented Reality Needle Guidance System and Multi-Modal Brain Connectivity Visualization for Pre-Surgical Planning" ====
+**July 08, 2020 : Shared meeting with the VASST team** \\
-Présenté par : Denis Kikinov
+  * **Speaker:** Maxime Peralta\\
-"I will introduce my ongoing industrial project: a lightweight training simulator that allows clinicians and trainees to practise intramuscular injections. The system allows viewing of the underlying muscles when injecting with a syringe, provides EMG feedback and provides visual guidance in the case that the user wants to target a specific muscle. Our prototype is composed of a synthetic arm model (comprised of muscles, bones, simulated fat and skin), real syringes and needles, and android tablet, and a support frame. Although a prototype has been created, it has yet to be tested among clinicians.
+**June 30, 2020 : Paper presentation : Advancing Our Understandings of Healthcare Team Dynamics From the Simulation Room to the Operating Room: A Neurodynamic Perspective** \\
-In my presentation I will also introduce our new mobile device AR application based on data derived from advanced imaging processing of neuroimaging data for both a healthy brain, and one with a brain tumour. The application uses a multi-modal approach implementing the structural and functional connectivity of the specified patient’s anatomy and visualizes their brain in augmented reality. This approach allows the user to interact in real time with the neuroanatomy in the context of its associated SC and FC. The project is very lightweight, requiring only an Android device and a couple pieces of paper."
+  * **Speaker:** Thibaut Dognon\\
+  * **Sumarry:** The initial models of team and team member dynamics using biometric data in healthcare will likely come from simulations. But how confident are we that the simulation-derived high-resolution dynamics will reflect those of teams working with live patients? We have developed neurodynamic models of a neurosurgery team while they performed a peroneal nerve decompression surgery on a patient to approach this question. The models were constructed from EEG-derived measures that provided second-by-second estimates of the neurodynamic responses of the team and team members to task uncertainty. The anesthesiologist and two neurosurgeons developed peaks, often coordinated, of elevated neurodynamic organization during the patient preparation and surgery which were similar to those seen during simulation training, and which occurred near important episodes of the patient preparation and surgery. As the analyses moved down the neurodynamic hierarchy, and the simulation and live patient neurodynamics occurring during the intubation procedure were compared at progressively smaller time scales, differences emerged across scalp locations and EEG frequencies. The most significant was the pronounced suppression of gamma rhythms detected by the frontal scalp sensors during the live patient intubation which was absent in simulation trials of the intubation procedure. These results indicate that while profiles of the second-by-second neurodynamics of teams were similar in both the simulation and live patient environments, a deeper analysis revealed differences in the EEG frequencies and scalp locations of the signals responsible for those team dynamics. As measures of individual and team performance become more micro-scale and dynamic, and simulations become extended into virtual environments, these results argue for the need for parallel studies in live environments to validate the dynamics of cognition being observed.
-===== Mardi 10 Septembre 2019 13:00-14:00 =====
+**June 22, 2020 : Paper presentation : Optimization of targeting specific areas by optimization of medical image processing methods based on deep learning** \\
+  * **Speaker:** Quoc-Anh Bui\\
+  * **Sumarry:** Transcranial Magnetic Stimulation treatment is a therapeutic technique that targets a specific area of the brain, in a non-invasive way. Individual positioning of the instruments for each patient improves the quality and effectiveness of the treatment. Therefore, improving the existing registration algorithm is necessary to improve the robustness, accuracy, reproducibility and preprocessing time of imaging data.
-==== "Improving activity recognition based on a priori about surgeon biomechanical behavior" ====
+**June 18, 2020 : Paper presentation : Person-Based Versus Generalized Impulsivity Disinhibition in Frontotemporal Dementia and Alzheimer Disease** \\
-Présenté par : Zakaria Kaddour
+  * **Speaker:** Delphine Tanguy\\
+  * **Sumarry:** Background: While much disinhibition in dementia results from generalized impulsivity, in behavioral variant frontotemporal dementia (bvFTD) disinhibition may also result from impaired social cognition. Objective: To deconstruct disinhibition and its neural correlates in bvFTD vs. early-onset Alzheimer’s disease (eAD). Methods: Caregivers of 16 bvFTD and 21 matched-eAD patients completed the Frontal Systems Behavior Scale disinhibition items. The disinhibition items were further categorized into (1) ‘‘person-based’’ subscale which predominantly associated with violating social propriety and personal boundary and (2) ‘‘generalized impulsivity’’ subscale which included nonspecific impulsive acts. Subscale scores were correlated with grey matter volumes from tensor-based morphometry on magnetic resonance images. Results: In comparison to the eAD patients, the bvFTD patients developed greater person-based disinhibition (P < 0.001) but comparable generalized impulsivity. Severity of person-based disinhibition significantly correlated with the left anterior superior temporal sulcus (STS), and generalized-impulsivity correlated with the right orbitofrontal cortex (OFC) and the left anterior temporal lobe (aTL). Conclusions: Person-based disinhibition was predominant in bvFTD and correlated with the left STS. In both dementia, violations of social propriety and personal boundaries involved fronto-parieto-temporal network of Theory of Mind, whereas nonspecific disinhibition involved the OFC and aTL.
-"Robot assisted surgery has been a rising research field in the past few year with the introduction of the da Vinci Research Kit and similar tools and in order to supply better assistance the robot requires knowledge about the task performed by the surgeon. In this presentation I will talk about my previous work on the anatomy training VR platform and I move to talking about my current work which revolves around defining a constraint based on kinematic data collected from the surgeon during the surgery and use prior knowledge about the task as a whole and on the different gestures comprising it to improve activity recognition. This work can be done through the application of a LSTM deep learning model based on the kinematic data introduced with the priori."
+**June 02, 2020 : Assessing scrub nurses' non-technical skills in a virtual and collaborative environement** \\
+  * **Speaker:** Marie-Stéphanie Bracq\\
+  * **Sumarry:** This research is part of a multidisciplinary project to develop a virtual reality (VR) training environment in non-technical skills (NTS) for scrub nurses. The objective of this thesis was to provide the partners with the choice of NTS, to define training scenarios and to provide a first proof of concept on a targeted population. According to the literature and interviews with expert scrub nurses, the NTS selected for the scenarios are situation awareness (SA) and speaking up. Study 1, carried out with 13 scrub nurses and 16 non-experts, aims to assess the acceptability of the environment with the "instrumentation table" scenario (under VR helmet). Study 2, involving 18 scrub nursing students and 8 scrub nurses during an in-service course, aims to develop situation awareness, using the "virtual operating room of errors" scenario (under VR helmet). This scenario enables SA to be assessed and seems a suitable training tool for this NTS. Finally, Study 3, involving 33 scrub nursing students, aims to develop speaking up with a tablet scenario. Our results partially confirm the effect of status on the probability of speaking up and show an effect of status on the discomfort of speaking up. Each study involved numerous exchanges with the project's VR engineers and scrub nursing teachers in order to allow the construction of the environment and its future integration into the scrub nursing school pedagogy. Finally, for each study, specific assessment tools were used and simulation sessions were developed according to recommendations with briefing, simulation, debriefing (HAS, 2012).
-===== Mardi 04 Juin 2019 13:00-14:00 =====
+**May 26, 2020 : Paper presentation : Advancing Our Understandings of Healthcare Team Dynamics From the Simulation Room to the Operating Room: A Neurodynamic Perspective** \\
+  * **Speaker:** Thibaut Dognon\\
+  * **Sumarry:** The initial models of team and team member dynamics using biometric data in healthcare will likely come from simulations. But how confident are we that the simulation-derived high-resolution dynamics will reflect those of teams working with live patients? We have developed neurodynamic models of a neurosurgery team while they performed a peroneal nerve decompression surgery on a patient to approach this question. The models were constructed from EEG-derived measures that provided second-by-second estimates of the neurodynamic responses of the team and team members to task uncertainty. The anesthesiologist and two neurosurgeons developed peaks, often coordinated, of elevated neurodynamic organization during the patient preparation and surgery which were similar to those seen during simulation training, and which occurred near important episodes of the patient preparation and surgery. As the analyses moved down the neurodynamic hierarchy, and the simulation and live patient neurodynamics occurring during the intubation procedure were compared at progressively smaller time scales, differences emerged across scalp locations and EEG frequencies. The most significant was the pronounced suppression of gamma rhythms detected by the frontal scalp sensors during the live patient intubation which was absent in simulation trials of the intubation procedure. These results indicate that while profiles of the second-by-second neurodynamics of teams were similar in both the simulation and live patient environments, a deeper analysis revealed differences in the EEG frequencies and scalp locations of the signals responsible for those team dynamics. As measures of individual and team performance become more micro-scale and dynamic, and simulations become extended into virtual environments, these results argue for the need for parallel studies in live environments to validate the dynamics of cognition being observed.
-==== "Situation awareness in the “Virtual Operating Room of Errors”: a pilot study" ====
+**May 26, 2020 : Paper presentation : Connectivity predicts deep brain stimulation outcome in Parkinson Disease** \\
-Présenté par : Marie-Stéphanie Bracq
+  * **Speaker:** Alfonso Estudillo\\
+  * **Sumarry:** Objective: The benefit of deep brain stimulation (DBS) for Parkinson disease (PD) may depend on connectivity between the stimulation site and other brain regions, but which regions and whether connectivity can predict outcome in patients remain unknown. Here, we identify the structural and functional connectivity profile of effective DBS to the subthalamic nucleus (STN) and test its ability to predict outcome in an independent cohort. Methods: A training dataset of 51 PD patients with STN DBS was combined with publicly available human connectome data (diffusion tractography and resting state functional connectivity) to identify connections reliably associated with clinical improvement (motor score of the Unified Parkinson Disease Rating Scale [UPDRS]). This connectivity profile was then used to predict outcome in an independent cohort of 44 patients from a different center. Results: In the training dataset, connectivity between the DBS electrode and a distributed network of brain regions correlated with clinical response including structural connectivity to supplementary motor area and functional anticorrelation to primary motor cortex (p < 0.001). This same connectivity profile predicted response in an independent patient cohort (p < 0.01). Structural and functional connectivity were independent predictors of clinical improvement (p < 0.001) and estimated response in individual patients with an average error of 15% UPDRS improvement. Results were similar using connectome data from normal subjects or a connectome age, sex, and disease matched to our DBS patients. Interpretation: Effective STN DBS for PD is associated with a specific connectivity profile that can predict clinical outcome across independent cohorts. This prediction does not require specialized imaging in PD patients themselves.
-"Training healthcare professionals in non-technical skills has revealed a crucial issue for patient safety and quality of care. Simulation offers good opportunities to follow that goal. Technologies for simulation are emerging, among which, virtual reality (VR). Yet, few VR simulators address non-technical skills. The “Virtual Operating Room of errors” scenario aims at training situation awareness in a VR environment."
+**May 11, 2020 : Paper presentation : Intraoperative Localization of STN During DBS Surgery Using a Data-Driven Model** \\
+  * **Speaker:** Thibault Martin\\
+  * **Sumarry:** A new approach is presented for localizing the Subthalamic Nucleus (STN) during Deep Brain Stimulation (DBS) surgery based on microelectrode recordings (MERs). DBS is an accepted treatment for individuals living with Parkinson’s Disease (PD). This surgery involves implantation of a permanent electrode inside the STN to deliver electrical current. Since the STN is a very small region inside the brain, accurate placement of an electrode is a challenging task for the surgical team. Prior to placement of the permanent electrode, microelectrode recordings of brain activity are used intraoperatively to localize the STN. The placement of the electrode and the success of the therapy depend on this location. In this paper,  an objective approach is implemented to help the surgical team in localizing the STN. This is achieved by processing the MER signals and extracting features during the surgery to be used in a Machine Learning (ML) algorithm for defining the neurophysiological borders of the STN. For this purpose, a new classification approach is proposed with the goal of detecting both the dorsal and the ventral borders of the STN during the surgical procedure. Results collected from 100 PD patients in this study, show that by calculating and extracting wavelet transformation features from MER signals and using a data-driven computational deep neural network model, it is possible to detect the borders of the STN with an accuracy of 92%. The proposed method can be implemented in real-time during the surgery to model the neurophysiological nonlinearity along the path of the electrode trajectory during insertion
-===== Lundi 27 Mai 2019 13:00-14:00 =====
+**May 05, 2020 : Paper presentation : Deep Double Descent: Where Bigger Models and More Data Hurt** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. Moreover, we show that double descent occurs not just as a function of model size, but also as a function of the number of training epochs. We unify the above phenomena by defining a new complexity measure we call the effective model complexity and conjecture a generalized double descent with respect to this measure. Furthermore, our notion of model complexity allows us to identify certain regimes where increasing (even quadrupling) the number of train samples actually hurts test performance
-==== "Sub-cortical shape alteration analysis for automated Parkinson Disease Diagnosis with Machine Learning" ====
+**May 05, 2020 : Paper presentation : Development of an Interactive Dashboard to Analyze Cognitive Workload of Surgical Teams During Complex Procedural Care** \\
-Présenté par : Maxime Peralta
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** In the surgical setting, team members constantly deal with a high-demand operative environment that requires simultaneously processing a large amount of information. In certain situations, high demands imposed by surgical tasks and other sources may exceed team member's cognitive capacity, leading to cognitive overload which may place patient safety at risk. In the present study, we describe a novel approach to integrate an objective measure of team member's cognitive load with procedural, behavioral and contextual data from real-life cardiac surgeries. We used heart rate variability analysis, capturing data simultaneously from multiple team members (surgeon, anesthesiologist and perfusionist) in a real-time and unobtrusive manner. Using audio-video recordings, behavioral coding and a hierarchical surgical process model, we integrated multiple data sources to create an interactive surgical dashboard, enabling the analysis of the cognitive load imposed by specific steps, substeps and/or tasks. The described approach enables us to detect cognitive load fluctuations over time, under specific conditions (e.g., emergencies, teaching) and in situations that are prone to errors. This in-depth understanding of the relationship between cognitive load, task demands and error occurrence is essential for the development of cognitive support systems to recognize and mitigate errors during complex surgical care in the operating room.
-"Brain morphometry is still considered as a secondary source of information for the diagnosis of Parkinson Disease. Indeed, clinical teams mostly make their diagnosis with clinical biomarkers. However, the increasing accuracy of MRI acquisition encourages research toward finding reliable and easy to acquire morphometric biomarkers to diagnose, track and monitor the progression of the disease. Among the techniques explored to analyze the morphometric variations occurring in Parkinson Disease, shape analysis has proved itself more reliable and consistent than volume analysis, thickness analysis and volume analysis. Several studies tried to evaluate the significance of subcortical shape displacements as a diagnosis biomarker for Parkinson Disease, leading to often contradictory results.
+**April 28, 2020 : Paper presentation : Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance** \\
+  * **Speaker:** Julien Berthelemy\\
+  * **Sumarry:** Dynamical systems can generate movement trajectories that are robust against perturbations. This article presents an improved modification of the original dynamic movement primitive (DMP) framework by Ijspeert et al [1], [2]. The new equations can generalize movements to new targets without singularities and large accelerations. Furthermore, the new equations can represent a movement in 3D task space without depending on the choice of coordinate system (invariance under invertible affine transformations). Our modified DMP is motivated from biological data (spinal-cord stimulation in frogs) and human behavioral experiments. We further extend the formalism to obstacle avoidance by exploiting the robustness against perturbations: an additional term is added to the differential equations to make the robot steer around an obstacle. This additional term empirically describes human obstacle avoidance. We demonstrate the feasibility of our approach using the Sarcos Slave robot arm: after learning a single placing movement, the robot placed a cup between two arbitrarily given positions and avoided approaching obstacles.
-I will present you, in this noon sharing, a fully automated pipeline for sub-cortical alteration analysis involving, for the fist time in the litterature, machine learning. This pipeline is able to successfully classify several cohorts of PD patients with various disease severity, as well as an healthy control cohort, thus showing that crucial informations correlated to disease severity are embedded into bilateral caudate nucleus and putamen."
+**April 14, 2020 : Academic background and PhD project** \\
+  * **Speaker:** Delphine Tanguy\\
+  * **Sumarry:** A quick summary of my academic background followed by a presentation of my thesis project: the neural basis of disinhibition in neurodegenerative diseases. This will be a first introduction to my PhD project and a description of the protocols used, without any results presentation
-===== Mardi 14 Mai 2019 13:00-14:00 =====
+**April 07, 2020 : Overview of my past projects** \\
+  * **Speaker:** Alfonso Estudillo\\
+  * **Sumarry:** In this meeting I am going to introduce a bit of myself, where I came from and what I did in my master and PhD theses. I am going to also show some projects I have involved with and finally the current project at MediCIS.
-==== "Overview of automatic classification methods to assess the skills of the surgeon during training using the kinematics data" ====
+**March 06, 2020 : History of Medecine, Study of medical and surgical knowledge and practices over time** \\
-Présenté par : Julien Berthélemy
+  * **Speaker:** Alicia Diot\\
+  * **Sumarry:** The History of Medicine is the study of medical and surgical knowledge and practices over time. Thanks to the discoveries of traces of ancient medical knowledge, we understand that medical practice has always existed, the fight against pain and infirmity is as old as Humanity. What has evolved over the centuries are the means used in this fight, from magic to modern scanners, from shamans to specialized surgeons ... Medicine is a discipline at the crossroads between Art and Science. From the origin of civilizations, it has been considered as an art, in the measure of intuition, empiricism, psychology ... Over time and with progress, it has become a science, based on the understanding of the human and its pathologies, on the identification of therapeutics, and the discovery of new techniques. Thus, while the art of healing is as old as mankind, Medicine as we know it today only dates back to the beginning of the 19th century. Since then, progress has continued at an impressive speed that keeps accelerating. It therefore seems difficult to retrace the evolution of Medicine in an exhaustive way, however, I will outline the main stages and dominant discoveries that have given rise to today’s medicine. It is important to understand that the division into chronological periods that I use in this presentation remains very artificial, the evolutions are actually very intertwined. Likewise, the great names that I cite as having largely contributed to the evolution of Medicine, are ultimately only a tiny part of the crowd that has participated in this evolution.
-"I will present a few studies about the automatic assessment of the surgeon's skills based on recordings of the kinematics data during a training exercice. Every article I will present uses a different method of machine learning or deep learning on the same JIGSAWS dataset. After that, I will compare the results of those classification methods and discuss them in order to develop my own method based on the ones giving the most promising results."
+**February 11, 2020 : Topology-Aware Activation Layer for Neural Network Image Segmentation** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** One of the recent developments in deep learning is the ability to train extremely deep residual neural networks, knowing that each residual block produces only marginal changes to the data. The accumulation of these changes result in the network's improved performance, analogous to a complex but trainable iterative algorithm. This intuition can be merged with the underlying theory of probabilistic graphical models in which these iterative algorithms are common and share the underlying probabilistic and information theoretic basis as deep learning. Prior models have been proposed with limitations on the number of iterations allowed in the solution algorithm due to the linear memory growth during the training process. This paper presents a structured activation layer which implements a conditional random field along with an arbitrary iteration message-passing marginal probability estimation algorithm which requires constant, rather than linear, memory with respect to the number of iterations. In this activation layer, the segmentation labels can be specified hierarchically, incorporating a level of abstract structure and some basic geometrical knowledge directly and easily into the network. Thus, this layer allows for the separation of abstract knowledge brought in by the network designer (in the form of the hierarchical structure) from probabilistic priors learned by the neural network. Preliminary results comparing this activation function to softmax and a similar non-hierarchical activation function indicate that it significantly improves performance in segmentation problems.
-===== Mardi 30 Avril 2019 13:00-14:00 =====
+**February 11, 2020 : Localisation of the Subthalamic Nucleus in MRI via Convolution Neural Networks for Deep Brain Stimulation Planning** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Deep brain stimulation (DBS) is an interventional treatment for Parkinson's disease in which electrodes are placed into specific locations in the basal ganglia to alleviate symptoms such as tremor and dyskinesia. Due to the small size and low contrast of specific targets of interest, such as the subthalamic nucleus (STN), localisation of these structures from pre-operative MRI is of great value. These localisation approaches are often atlas-based, using registration algorithms to align patient images with a prior annotated atlas. However, these methods require a large amount of time, especially for correctly estimating deformation fields, or are prone to error for smaller structures such as the STN. This paper investigates two deep learning frameworks for the localisation of the stn from T1- and T2-weighted MRI using convolutional neural networks which estimate its centroid. These methods are compared against an atlas-based segmentation using the ParkMedAtlis v3 atlas, showing an improvement in localisation error in the range of ~0.5-1.3 mm with a reduction of orders of magnitude of computation time. This method of STN localisation will allow us in future to automatically identify the STN for DBS surgical planning as well as define a greatly reduced region-of-interest for more accurate segmentation of the STN.
-==== "How brain connectivity could help to predict DBS clinical outcomes ?" ====
+**January 28, 2020 : Clinical and technological study of the spine biomechanics, scoliosis-oriented** \\
-Présenté par : Tristan Moreau
+  * **Speaker:** Kevin Le Mut\\
+  * **Sumarry:** Scoliosis is the largest three-dimensional deformation in the human body. It causes many health issues and there is a lack of data to correct them properly. Surgeons can only use their experience to operate. The role of biomechanics and finite element simulations is to provide more data and to analyze the constraints within the spine.
-"Detailed anatomical knowledge and quantification of white matter properties are of particular therapeutic importance for Deep Brain Stimulation (DBS), an invasive neuromodulatory therapy which aims to balance disorganized motor circuits by applying high-frequency current to a target nucleus within basal ganglia. This presentation will take the form of a discussion around some interesting papers."
+**January 21, 2020 : Convolutional Neural Network for Localizing the Subthalamic Nucleus Using One Second Micro-electrode Recordings** \\
+  * **Speaker:** Maxime Peralta\\
+  * **Sumarry:** Micro-electrode recording (MER) is a powerful way of localizing target structures during neurosurgical procedures such as the implantation of deep brain stimulation electrodes which is a common treatment for Parkinson's disease and other neurological disorders. Although allowing better clinical results than guiding only with per-operative imaging, MER is not unanimously used in clinic, notably because of its long duration which can lead to complications during the operation, and because it requries a high degree of expertise. Different approaches towards automating MER analysis and structure localization have been proposed on the last decade, mainly focused on feature engineering. While the accuracies obtained are good in certain configurations, one issue with handcrafted features is that they do not necessarily capture more subtle differences in MER that are detected by expert neurophysiologists by ear. In this presentation, i'll show you a deep learning based pipeline for subthalamic nucleus (STN) localization with micro-electrode recordings which is motivated by the human auditory system. The proposed Convolutional Neural Network (CNN) shows improved accuracy over two comparative networks for locating the STN from one second MERs.
+**January 07, 2020 : Kinematic data analysis for skill assessment in surgery: a review** \\
+  * **Speaker:** Julien Berthelemy\\
-===== Mardi 02 Avril 2019 13:00-14:00 =====
-==== "Introduction aux modèles graphiques probabilistes" ====
+===== 2019 =====
-Présenté par : John Baxter
+**October 22, 2019 : Elephants in the Room:  How should we analyse trainee performance on simulator-based scenarios?** \\
+  * **Speaker:** Roy Eagleson\\
-"Ma présentation est une introduction aux modèles graphiques probabilistes, spécifiquement les modèles max-flow, et leur intégration dans le cadre de l’apprentissage profond. Ces modèles nous permettent d’ajouter directement l’information topologique dans un réseau de neurones artificiels pendant son apprentissage et son application. La présentation inclura une explication brève sur les modèles max-flow et leurs solutions approximatives, les problèmes avec la combinaison de ces modèles et de l’apprentissage automatique, et DeepFlow qui vise à résoudre ces problèmes pour la segmentation d’images."
+**October 08, 2019 : What will happen to you if you go in medical device industry** \\
+  * **Speaker:** Ehouarn Maguet\\
+  * **Sumarry:** I will share with you some part of the daily life of a software engineer in a medical device industry. I will talk about medical standard (and try not to be boring), audit, impact of software and hardware on regulation, a resolution bug example, and some anecdotes.
-===== Mardi 26 Mars 2019 13:00-14:00 =====
+**October 01, 2019 : Cognitive Oriented Design and Assessment of Augmented Reality in Medicine** \\
+  * **Speaker:** Pierre Jannin\\
+  * **Sumarry:** Mixed and Augmented Reality (AR) is a technology that aims to augment the perception of reality by adding computer-generated information. Such technology has been applied for medical procedures (especially surgery) the past 20 years to help physicians understand and perform procedures, as well as for training. However, as outlined in different review papers, AR has not yet reached its full potential usefulness and implementation in the medical workflow. Many reasons for this have been expressed; one is that the AR system design approach is mainly technology driven, resulting in the need to develop relevant and clinically valuable AR applications. Another reason is the lack of relevant assessments of proposed AR systems to validate their benefits in all aspects of medical care. In this presentation, I will suggest a cognitive-oriented approach for both optimal design and assessment of AR systems. This approach is based on two main statements: (1) ensuring proper definition and modeling of medical objective(s) and (2) considering understanding as the main motivation for AR.
-==== "Future work regarding CARS conference and MediCIS' website" ====
+**September 17, 2019 : Augmented Reality Needle Guidance System and Multi-Modal Brain Connectivity Visualization for Pre-Surgical Planning** \\
-Présenté par : Pierre Jannin
+  * **Speaker:** Denis Kikinov\\
+  * **Sumarry:** I will introduce my ongoing industrial project: a lightweight training simulator that allows clinicians and trainees to practise intramuscular injections. The system allows viewing of the underlying muscles when injecting with a syringe, provides EMG feedback and provides visual guidance in the case that the user wants to target a specific muscle. Our prototype is composed of a synthetic arm model (comprised of muscles, bones, simulated fat and skin), real syringes and needles, and android tablet, and a support frame. Although a prototype has been created, it has yet to be tested among clinicians. In my presentation I will also introduce our new mobile device AR application based on data derived from advanced imaging processing of neuroimaging data for both a healthy brain, and one with a brain tumour. The application uses a multi-modal approach implementing the structural and functional connectivity of the specified patient’s anatomy and visualizes their brain in augmented reality. This approach allows the user to interact in real time with the neuroanatomy in the context of its associated SC and FC. The project is very lightweight, requiring only an Android device and a couple pieces of paper.
-"This week's lab meeting will mainly be about two subjects : the organisation of the CARS conference and the evolution of the MediCIS website.
+**September 10, 2019 : Improving activity recognition based on a priori about surgeon biomechanical behavior** \\
+  * **Speaker:** Zakaria Kaddour\\
+  * **Sumarry:** Robot assisted surgery has been a rising research field in the past few years with the introduction of the da Vinci Research Kit and similar tools and in order to supply better assistance the robot requires knowledge about the task performed by the surgeon. In this presentation I will talk about my previous work on the anatomy training VR platform and I move to talking about my current work which revolves around defining a constraint based on kinematic data collected from the surgeon during the surgery and use prior knowledge about the task as a whole and on the different gestures comprising it to improve activity recognition. This work can be done through the application of a LSTM deep learning model based on the kinematic data introduced with the priori.
-As you all know, the CARS conference is coming up which means we should take time to discuss once again about how each of us will take part in this project as well as present what has already been done.
+**June 04, 2019 : Situation awareness in the “Virtual Operating Room of Errors”: a pilot study** \\
+  * **Speaker:** Marie-Stéphanie Bracq\\
+  * **Sumarry:** Training healthcare professionals in non-technical skills has revealed a crucial issue for patient safety and quality of care. Simulation offers good opportunities to follow that goal. Technologies for simulation are emerging, among which, virtual reality (VR). Yet, few VR simulators address non-technical skills. The “Virtual Operating Room of errors” scenario aims at training situation awareness in a VR environment.
-When it comes to the MediCIS website, the goal of this meeting will be to discuss what could or should be done to renew it."
+**May 27, 2019 : Sub-cortical shape alteration analysis for automated Parkinson Disease Diagnosis with Machine Learning** \\
+  * **Speaker:** Maxime Peralta\\
+  * **Sumarry:** Brain morphometry is still considered as a secondary source of information for the diagnosis of Parkinson Disease. Indeed, clinical teams mostly make their diagnosis with clinical biomarkers. However, the increasing accuracy of MRI acquisition encourages research toward finding reliable and easy to acquire morphometric biomarkers to diagnose, track and monitor the progression of the disease. Among the techniques explored to analyze the morphometric variations occurring in Parkinson Disease, shape analysis has proved itself more reliable and consistent than volume analysis, thickness analysis and volume analysis. Several studies tried to evaluate the significance of subcortical shape displacements as a diagnosis biomarker for Parkinson Disease, leading to often contradictory results. I will present you, in this noon sharing, a fully automated pipeline for sub-cortical alteration analysis involving, for the first time in the literature, machine learning. This pipeline is able to successfully classify several cohorts of PD patients with various disease severity, as well as a healthy control cohort, thus showing that crucial information correlated to disease severity are embedded into bilateral caudate nucleus and putamen.
-===== Mardi 19 Mars 2019 13:00-14:00 =====
+**May 14, 2019 : Overview of automatic classification methods to assess the skills of the surgeon during training using the kinematics data** \\
+  * **Speaker:** Julien Berthélemy\\
+  * **Sumarry:** I will present a few studies about the automatic assessment of the surgeon's skills based on recordings of the kinematics data during a training exercice. Every article I will present uses a different method of machine learning or deep learning on the same JIGSAWS dataset. After that, I will compare the results of those classification methods and discuss them in order to develop my own method based on the ones giving the most promising results.
-==== "Treating chronic pain using neuronavigated Transcranial Magnetic Stimulation (TMS)" ====
+**April 30, 2019 : How brain connectivity could help to predict DBS clinical outcomes ?** \\
-Présenté par : Syneika
+  * **Speaker:** Tristan Moreau\\
+  * **Sumarry:** Detailed anatomical knowledge and quantification of white matter properties are of particular therapeutic importance for Deep Brain Stimulation (DBS), an invasive neuromodulatory therapy which aims to balance disorganized motor circuits by applying high-frequency current to a target nucleus within basal ganglia. This presentation will take the form of a discussion around some interesting papers.
-"Up to 7% of the general population suffers from neuropathic pain which comes from various sources such as neurological diseases or peripheral nerve lesions. However, more than half of these patients say they are not relieved by their medical treatment. Neuronavigated Transcranial Magnetic Stimulation (TMS) is a non-invasive and virtually painless therapy that modulates the activity of precise neural networks of the cerebral cortex using high intensity magnetic pulses. TMS has demonstrated its effectiveness in the treatment of several neurological and psychiatric diseases.
+**April 02, 2019 : Introduction aux modèles graphiques probabilistes** \\
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Ma présentation est une introduction aux modèles graphiques probabilistes, spécifiquement les modèles max-flow, et leur intégration dans le cadre de l’apprentissage profond. Ces modèles nous permettent d’ajouter directement l’information topologique dans un réseau de neurones artificiels pendant son apprentissage et son application. La présentation inclura une explication brève sur les modèles max-flow et leurs solutions approximatives, les problèmes avec la combinaison de ces modèles et de l’apprentissage automatique, et DeepFlow qui vise à résoudre ces problèmes pour la segmentation d’images.
+**March 26, 2019 : Future work regarding CARS conference and MediCIS' website** \\
+  * **Speaker:** Pierre Jannin\\
+  * **Sumarry:** This week's lab meeting will mainly be about two subjects: the organisation of the CARS conference and the evolution of the MediCIS website. As you all know, the CARS conference is coming up which means we should take time to discuss once again about how each of us will take part in this project as well as present what has already been done. When it comes to the MediCIS website, the goal of this meeting will be to discuss what could or should be done to renew it.
-Syneika offers a complete and accurate solution of neuronavigated Transcranial Magnetic Stimulation, and allows each doctor to individualize his treatment by taking into account the anatomy of each patient. A solution that can also be used very simply by the healthcare team."
+**March 19, 2019 : Treating chronic pain using neuronavigated Transcranial Magnetic Stimulation (TMS)** \\
+  * **Speaker:** Syneika\\
+  * **Sumarry:** Up to 7% of the general population suffers from neuropathic pain which comes from various sources such as neurological diseases or peripheral nerve lesions. However, more than half of these patients say they are not relieved by their medical treatment. Neuronavigated Transcranial Magnetic Stimulation (TMS) is a non-invasive and virtually painless therapy that modulates the activity of precise neural networks of the cerebral cortex using high intensity magnetic pulses. TMS has demonstrated its effectiveness in the treatment of several neurological and psychiatric diseases. Syneika offers a complete and accurate solution of neuronavigated Transcranial Magnetic Stimulation, and allows each doctor to individualize his treatment by taking into account the anatomy of each patient. A solution that can also be used very simply by the healthcare team.
-===== Mardi 5 Fevrier 2019 13:00-14:00 =====
+**February 05, 2019 : Automatic annotation of surgical procedures** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Annotation of surgical activities becomes increasingly important for many recent applications such as surgical workflow analysis, surgical situation awareness and the design of the operating room of the future, especially to train machine learning methods in order to develop intelligent assistance. Currently, annotation is mostly performed by observers with medical background and is incredibly costly and time-consuming, creating a major bottleneck for the above-mentioned technologies. However, meaningful information about interaction between objects is inherently available in virtual-reality environments. We propose a strategy to convert automatically this information into annotations in order to provide as output individual surgical process models. We implemented our approach through a peg-transfer task simulator and compared it to manual annotations performed by six members of the lab.
-==== "Automatic annotation of surgical procedures" ====
+**January 31, 2019 : Comprendre et maîtriser les facteurs humains et organisationnels pouvant influencer les résultats individuels du chirurgien** \\
-Présenté par : Arnaud Huaulme
+  * **Speaker:** Antoine Duclos\\
+  * **Sumarry:** Cette présentation abordera la mesure, l’interprétation et la maîtrise des résultats individuels du chirurgien. Un premier axe méthodologique ciblera le développement d’indicateurs et d’outils graphiques pour guider les chirurgiens vers une meilleure compréhension de leur performance. Un second axe questionnera la courbe de performance des chirurgiens tout au long de leur carrière avec l’espoir d’identifier des facteurs humains et organisationnels susceptibles d’améliorer la qualité, la sécurité et l’efficience des procédures réalisées sur le patient dans le contexte du bloc opératoire.
-"Annotation of surgical activities becomes increasingly important for many recent applications such as surgical workflow analysis, surgical situation awareness and the design of the operating room of the future, especially to train machine learning methods in order to develop intelligent assistance. Currently, annotation is mostly performed by observers with medical background and is incredibly costly and time-consuming, creating a major bottleneck for the above-mentioned technologies. However, meaningful information about interaction between objects is inherently available in virtual-reality environments. We propose a strategy to convert automatically this information into annotations in order to provide as output individual surgical process models. We implemented our approach through a peg-transfer task simulator and compared it to manual annotations performed by six members of the lab."
+**January 22, 2019 : Medical data Translation for semantic storage** \\
+  * **Speaker:** Marine Brenet\\
+  * **Sumarry:** I will be presenting my work for the Medirad Project. For this project many medical data will be used. My server will translate all these data from european countries to store them and allow easy and powerfull querring.
-===== Jeudi 31 Janvier 2019 13:00-14:00 =====
+**January 15, 2019 : Presentation of the pyDBS project** \\
+  * **Speaker:** Boubacar Ndack\\
+  * **Sumarry:** For the next noon sharing, I will present the pyDBS project. As you know, the project involves developing an image guidance and assistance environment for the Deep Brain Stimulation (DBS) neurosurgery procedure. This procedure involves implanting electrical stimulation electrodes deep into the brain, in order to target specific anatomical areas that will respond to the applied electrical stimulation. I'll do a little reminder of the deep brain stimulation. After that, I'll present our work on this project
-==== "Comprendre et maîtriser les facteurs humains et organisationnels pouvant influencer les résultats individuels du chirurgien" ====
+**January 08, 2019 : Overview of my first year of PhD** \\
-Présenté par : Antoine Duclos
+  * **Speaker:** Maxime Peralta\\
+  * **Sumarry:** For this noon sharing, i will quickly present the context and the objectives of my thesis, before presenting you the work i did so far. The first project is about clinical data compression using neural networks. The second one is the work done by Antoine Ackaouy and I on electrophysiological signal analysis. Finally, i'll present you the work i did in the team of Ali Khan at Robarts Imaging (London, Ontario, Canada), and the perspectives of this project.
-"Cette présentation abordera la mesure, l’interprétation et la maîtrise des résultats individuels du chirurgien. Un premier axe méthodologique ciblera le développement d’indicateurs et d’outils graphiques pour guider les chirurgiens vers une meilleure compréhension de leur performance. Un second axe questionnera la courbe de performance des chirurgiens tout au long de leur carrière avec l’espoir d’identifier des facteurs humains et organisationnels susceptibles d’améliorer la qualité, la sécurité et l’efficience des procédures réalisées sur le patient dans le contexte du bloc opératoire."
-===== Mardi 22 Janvier 2019 13:00-14:00 =====
-==== "Medical data Translation for semantic storage" ====
+===== 2018 =====
-Présenté par : Marine Brenet
+**December 11, 2018 : In beer we must trust!** \\
+  * **Speaker:** Ehouarn Maguet\\
+  * **Sumarry:** I will attempt to get you more interested in one central element of our society, beer and beer processing. France is historically a country of wine, but recently the world wide trend of craft beer invaded our country, and it tries to prove that beer can be as complex and creative as wine. I will talk about raw ingredients, some historical anecdotes, industrial beer VS local production, beer styles classification, etc. In a second part I will present you the three main steps of beer production, and try to convince you to brew your own beer at home !
-"I will be presenting my work for the Medirad Project. For this project many medical data will be used. My server will translate all these data from european countries to store them and allow easy and powerfull querring."
+**December 05, 2018 : Appel à participation et volontariat pour CARS 2019** \\
+  * **Speaker:** Pierre Jannin\\
+  * **Sumarry:** Pierre Jannin will make a presentation about the next edition of CARS which will take place in Rennes in June 2019. The goal of this meeting is to discuss the organisation of the next edition of CARS as well as how the members of the MediCIS team and the whole LTSI institute can take part in this project.
-===== Mardi 15 Janvier 2019 13:00-14:00 =====
+**November 27, 2018 : Virtual Reality for Healthcare** \\
+  * **Speaker:** Marie Le Duff\\
+  * **Sumarry:** Technology is changing the face of healthcare as we know it. Although VR tends to be associated with the entertainment genre and indeed set sails to enhance the demanding gamer’s experience, virtual environment are now becoming a real game-changer in healthcare, and has wide applications ranging from education, training, diagnosis and therapy. I will start my presentation with a brief introduction to VR technology and its history, and then present VR uses in medical environments. You will also be invited to try some VR experiences.
-==== "Presentation of the pyDBS project" ====
+**November 20, 2018 : Analysis and quantification of quality in laparoscopy based on spatial and temporal metrics.** \\
-Présenté par : Boubacar Ndack
+  * **Speaker:** Arthur Derathé\\
+  * **Sumarry:** We work on the evaluation of the surgical skills of confirmed surgeons during a real procedure based on the annotation of the temporal and the spatial aspects of the laparoscopic video, as well as the annotation of a quality score. Our methodology is to observe the behaviour of a machine learning algorithm as we optimize its hyper parameters. Of course our goal is to get the best prediction of the quality score, but I will discuss more closely how the metrics cluster (temporal or spatial) in input and the cross validation strategy influences the algorithm prediction. Finally I will introduce the next phase of my work, which is a close analysis of how do the input metrics behave in relation to the quality score, and how we can translate these analysis to the clinical realm.
-"For the next noon sharing, I will present the pyDBS project. As you know, the project involves developing an image guidance and assistance environment for the Deep Brain Stimulation (DBS) neurosurgery procedure. This procedure involves implanting electrical stimulation electrodes deep into the brain, in order to target specific anatomical areas that will respond to the applied electrical stimulation.
+**November 13, 2018 : Special presentation : CARS.** \\
+  * **Speaker:** Pierre Jannin\\
+  * **Sumarry:** After a quick and general presentation about what CARS is, we will discuss how the members of the MediCIS team and the whole LTSI institute can take part in this project.
-I'll do a little reminder of the deep brain stimulation. After that, I'll present our work on this project."
+**October 16, 2018 : Evaluation of surgical skills using physiological signals and machine learning, organisation of my work** \\
+  * **Speaker:** Thibaut Dognon\\
+  * **Sumarry:** The evaluation of surgical skills is usually based on observation which is limited both by the need for experts to be present and by the subjectivity of the examiner. The position of instruments or physiological measures recorded during a surgical procedure might be helpful to go beyond the subjectivity of the expert’s supervision. The goal of this study is to obtain unbiased, quantifiable and reproductible metrics to assess surgical skills. As the internship has ended and the PhD starts I will be presenting what has already been done, how I plan to organise my work as well as what I have learned during the internship that will benefit me for the completion of this project.
-===== Mardi 8 Janvier 2019 13:00-14:00 =====
+**October 09, 2018 : The use of virtual reality for non-technical skills.** \\
+  * **Speaker:** Marie-Stephanie Bracq\\
+  * **Sumarry:** I will present my work on the evaluation of scrub nurses' non-technical skills in a virtual environment. More specifically, I will present the results of my first study on the acceptability of the virtual training environment by experts (scrub nurses from the neurosurgery department of the University Hospital) as well as by non-experts (some of whom are lab members). I will then adress the next steps with the "operating room of errors" scenario, which is currently being finalised, and finally with the very rapid evocation of a scenario on communication currently being developed.
-==== "Overview of my first year of PhD" ====
+**September 25, 2018 : Special Noon Sharing : 90 to 120 seconds to pitch a crazy idea.** \\
-Présenté par : Maxime Peralta
+  * **Speaker:** Tout le laboratoire\\
-"For this noon sharing, i will quickly present the context and the objectives of my thesis, before presenting you the work i did so far. The first project is about clinical data compression using neural networks. The second one is the work done by Antoine Ackaouy and I on electrophysiological signal analysis. Finally, i'll present you the work i did in the team of Ali Khan at Robarts Imaging (London, Ontario, Canada), and the perspectives of this project."
+**June 29, 2018 : Goals, guidelines, and best practices: a framework for designing augmented reality ultrasound guidance systems; or if you build it, will they come?** \\
+  * **Speaker:** Golafsoun Ameri\\
+  * **Sumarry:** Real-time ultrasound has become a crucial aspect of several image-guided interventions. One of the main constraints of such an approach is the difficulty in interpretability of the limited field of view of the image, a problem that has recently been addressed using mixed reality environments, such as augmented reality (AR). The growing popularity and maturity of AR has led to a series of informal guidelines to direct development of new systems and to facilitate regulatory approval. However, the goals of AR image guidance systems and the guidelines for their development have not been thoroughly discussed. The purpose of this talk is to identify the goals, guidelines, and best practices for the development of AR ultrasound guidance and encourage discussion on the effective development of such systems.
-===== Mardi 11 Décembre 2018 13:00-14:00 =====
+**June 28, 2018 : Analysis of surgical skills using physiological signals.** \\
+  * **Speaker:** Thibaut Dognon\\
+  * **Sumarry:** With the increasing number of surgical procedures performed every year, the precise evaluation of surgical skills is crucial. This evaluation usually consists in a trainee performing a specific task and an examiner evaluating the quality of the procedure with a standardized score (NOTSS, GOALS, OSATS, etc.). This approach is limited both by the need for experts to be present and by the subjectivity of the examiner. Information taken from the position of instruments or physiological measures might be helpful to go beyond the subjectivity of the expert’s supervision. EEG signals have already been used to predict the performance of subjects during the training of sports-related skills. They have also been used to monitor the training improvements in a motor task or visuomotor sequence learning. Using machine or deep learning approaches and complex features from the EEG signals both in sensor and source space, this study aims at obtaining unbiased, quantifiable and reproductible metrics to assess surgical skills.
-==== "In beer we must trust!" ====
+**June 12, 2018 : Sequential surgical signatures in micro-suturing task.** \\
-Présenté par : Ehouarn Maguet
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Surgical processes are generally only studied by identifying differences in populations such as participants or level of expertise. But the similarity between populations is also important in understanding the process. We therefore proposed to study these two aspects. In this presentation, we will demonstrate the concept of sequential surgical signature thank to a pattern mining method applied to a micro-surgical suturing task data set.
-"I will attempt to get you more interested in one central element of our society, beer and beer processing. France is historically a country of wine, but recently the world wide trend of craft beer invaded our country, and it tries to prove that beer can be as complex and creative as wine. I will talk about raw ingredients, some historical anecdotes, industrial beer VS local production, beer styles classification, etc.
+**June 07, 2018 : Electroencephalography Source Connectivity: Aiming for High Resolution of Brain Networks in Time and Space** \\
-In a second part I will present you the three main steps of beer production, and try to convince you to brew your own beer at home !"
+  * **Speaker:** Mahmoud Hassan \\
+  * **Sumarry:** The human brain is a large-scale network the function of which depends on dynamic interactions between spatially distributed regions. In the rapidly evolving field of network neuroscience, two unresolved challenges hold the promise of potential breakthroughs. First, functional brain networks should be identified using noninvasive and easy-to-use neuroimaging techniques. Second, the time-space resolution of these techniques should be good enough to assess the dynamics of the identified networks. Emerging evidence suggests that the electroencephalography (EEG) source-connectivity method may offer solutions to both issues, provided that scalp EEG signals are appropriately processed. Therefore, this technique's performance strongly depends on signal processing that involves various methods, such as preprocessing approaches, inverse solutions, statistical couplings between signals, and network science.
-===== Mercredi 5 Décembre 2018 13:00-14:00 =====
+**May 31, 2018 : Special Noon Sharing: Your work in 90 seconds** \\
+  * **Speaker:** Tout le laboratoire\\
-==== "Appel à participation et volontariat pour CARS 2019" ====
+**May 24, 2018 : Interaction in medical image segmentation.** \\
-Présenté par : Pierre Jannin
+  * **Speaker:** John Baxter\\
+  * **Sumarry:** Human-computer interaction as a tool-kit is diverse but also infrequently used to provide the context behind movements in computer science. New developments in hardware and algorithms tend to take precedence in explaining these advancements more so than an understanding of how they are actually used. The goal of this set of presentations is to introduce concepts from human-computer interaction and how it applies to segmentation programs in order to help spur a more out-of-the-box thought process to a familiar topic
-"Pierre Jannin will make a presentation about the next edition of CARS which will take place in Rennes in June 2019. The goal of this meeting is to discuss the organisation of the next edition of CARS as well as how the members of the MediCIS team and the whole LTSI institute can take part in this project."
+**April 03, 2018 : Festivals de printemps et d'été à Rennes et autour.** \\
+  * **Speaker:** Gurvan Lecuyer\\
+  * **Sumarry:** My presentation is about the main music festivals of the spring and summer in Rennes, Brittany and around. The purpose of this presentation is to introduce newcomers to this incredible occasion to have fun while listening good music. I will present the lineup of each festivals and the experience you can expect for those I've attended.
-===== Mardi 27 Novembre 2018 13:00-14:00 =====
+**March 27, 2018 : Presentation of the differents ongoing projects of MediCIS** \\
+  * **Speaker:** Pierre Jannin\\
-==== "Virtual Reality for Healthcare." ====
+**March 20, 2018 : Presentation of the "Délégation à la Recherche Clinique et à l'Innovation (DRCI)"** \\
-Présenté par : Marie Le Duff
+  * **Speaker:** Loïc FIN\\
-"Technology is changing the face of healthcare as we know it. Although VR tends to be associated with the entertainment genre and indeed set sails to enhance the demanding gamer’s experience, virtual environment are now becoming a real game-changer in healthcare, and has wide applications ranging from education, training, diagnosis and therapy. I will start my presentation with a brief introduction to VR technology and its history, and then present VR uses in medical environments. You will also be invited to try some VR experiences."
+**March 12, 2018 : Simulation, performance and human factors in obstetrics and gynecology** \\
+  * **Speaker:** Maela LE LOUS\\
-===== Mardi 20 Novembre 2018 13:00-14:00 =====
+**February 20, 2018 : Exploring Fusion Models in Computer Vision for Medical Image Computing (part 2).** \\
+  * **Speaker:** Duygu Sarikaya\\
-==== "Analysis and quantification of quality in laparoscopy based on spatial and temporal metrics." ====
+**February 13, 2018 : Exploring Fusion Models in Computer Vision for Medical Image Computing.** \\
-Présenté par : Arthur Derathé
+  * **Speaker:** Duygu Sarikaya\\
+  * **Sumarry:** Automatic understanding of medical images has been an active research area, as a need for universally accepted, standard and validated metrics is addressed in the community.  The recent advances of computer vision and machine learning algorithms coupled with the use of digital imaging modalities has led to improvements in automatic understanding of medical imaging data. In this talk, we explore fusion models in computer vision for medical image computing. We propose solutions to the open problems of robot-assisted surgery (RAS) video understanding, and segmentation of the tumor and anatomical structures of the brain. Modeling the gestures and skill level of surgeons in robot-assisted surgery (RAS) videos presents an interesting problem. Early identification of technical competence in surgical skills is expected to help tailor training to personalized needs of surgeons in training. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. Characterization of anatomical structure of the brain in magnetic resonance human brain images (MRI) has also gained high interest in recent years. There is a strong need for a computer-aided system that will automatically and accurately define the tumor and anatomical structures of the brain. A universally-accepted, standardized automatic mapping and segmentation of brain volumetry would be a significant improvement for diagnosis, modeling personalized progression, and treatment monitoring of neurologic conditions. We show that exploiting the relationship across different tasks, jointly reasoning multi-tasks, and taking advantage of a combination of shared and task-specific representations, or using smart fusion of a priori knowledge inferred from multiple data sources for these problems perform astonishingly better than their single-task counterparts.
-"We work on the evaluation of the surgical skills of confirmed surgeons during a real procedure based on the annotation of the temporal and the spatial aspects of the laparoscopic video, as well as the annotation of a quality score. Our methodology is to observe the behaviour of a machine learning algorithm as we optimize its hyper parameters. Of course our goal is to get the best prediction of the quality score, but I will discuss more closely how the metrics cluster (temporal or spatial) in input and the cross validation strategy influences the algorithm prediction. Finally I will introduce the next phase of my work, which is a close analysis of how do the input metrics behave in relation to the quality score, and how we can translate these analysis to the clinical realm."
+**February 06, 2018 : Study of anatomo-clinical correlation in Deep Brain Stimulation by Machine Learning: A presentation of my thesis.** \\
+  * **Speaker:** Maxime Peralta\\
+  * **Sumarry:** Deep Brain Stimulation (DBS) is a surgical procedure used notably for conteract the motor effects of Parkinson Desease. Even though it shows promising results, several unknowns and difficulties remain. Artifical intelligence, through Machine Learning (ML) or Deep Learning (DL), is forseen to be one of the solution to come up with these issues. During this presentation, i will quickly introduce DBS and ML/DL. After that, i will present the objectives of my thesis by talking about the difficulties of using deep learning algorithms in neurosurgery and introducing tractography. I'll then present a study in progress with Clément Baumgarten and finish by introducing the objectives of my next study.
-===== Mardi 13 Novembre 2018 13:00-14:00 =====
+**January 30, 2018 : Relationships between Expertise, Team Familiarity and Surgical Workflow Disruptions: an Observational Study** \\
+  * **Speaker:** Pierre-Louis Henaux\\
+  * **Sumarry:** A workflow disruption (WD) is characterized by deviations from the natural progression of an operation, thus possibly compromising operation safety. Disruptions in the operating room (OR) can be subdivided into communication, usability, physical layout, environmental hazards, general interruptions and equipment failures. Communication failures in the OR can occur in approximately 30% of team exchanges and a third of these causes of WD endanger patient safety. Surgical errors are strongly related to number of WD.  Teamwork has been shown as an essential factor to reduce WD. Research in other high-risk settings such as in aviation field highlighted the fact that limited team familiarity (TF) between teammates can lead to negative safety outcomes. The aim of this exploratory study was to examine the relationships between expertise, TF and WD with scrub nurses (SN) and neurosurgeons through an observation of elective neurosurgical procedures carried out by surgeons and SN with different levels of expertise and different degrees of familiarity with each other.
-==== "Special presentation : CARS." ====
+**January 23, 2018 : Skill based assistance in robotic surgery.** \\
-Présenté par : Pierre Jannin
+  * **Speaker:** Atsushi Nakazawa\\
+  * **Sumarry:** Robotic surgery has gained increasing popularity in recent years. Intelligent robotic surgical assistance in surgical sub-tasks such as suturing has the potential to enhance surgeon's performance and reduce fatigue and operating time. Previous works in surgical automation use a replication of demonstrated motions or a planned path, but they are not necessarily skilled motions. Therefore, we aim to develop an assistance system in robotic surgery based on skill analysis. As a first step, we are working on environment recognition to get better understanding of the skills.
-"After a quick and general presentation about what CARS is, we will discuss how the members of the MediCIS team and the whole LTSI institute can take part in this project."
+**January 09, 2018 : Mental Representation during Preoperative Surgical Planning** \\
+  * **Speaker:** Pierre-Louis Henaux\\
+  * **Sumarry:** Expert judgment is vital for safe surgery. Judgment is difficult to define. A critical aspect of it is the ability of accurately mentally represent the purpose of surgical procedure. Mental Representation (MR) determines the details of this procedure, plans what decisions would be made, as well as what approaches would be taken and whether a procedure fits within a surgeon confort zone. Therefore, MR is critical to our understanding of surgical expertise. There is a body of literature about decision making, surgical intuition, clinical reasoning, problems solving. However, we should understand the essence of all these non-technical skills. MR is a process which underpins all these cognitive skills. Through a qualitative study following a constructivist grounded theory methodology, the aim of this study was to explore how does the surgeon mentally represent the operative procedure preoperatively and how this MR changes over time with development of surgical expertise.
-===== Mardi 16 octobre 2018 13:00-14:00 =====
-==== "Evaluation of surgical skills using physiological signals and machine learning, organisation of my work." ====
+===== 2017 =====
-Présenté par : Thibaut Dognon
+**December 19, 2017 : Development of an intelligent surgical training system for Thoracentesis** \\
+  * **Speaker:** Hiren Nakawala\\
+  * **Sumarry:** Surgical training improves patient care, helps to reduce surgical risks, increases surgeon’s confidence, and thus enhances overall patient safety. Current surgical training systems are more focused on developing technical skills, e.g. dexterity, of the surgeons while lacking the aspects of context-awareness and intra-operative real-time guidance. Context-aware intelligent training systems interpret the current surgical situation and help surgeons to train on surgical tasks. first part of the talk will introduce context-aware system framework which helps to identify surgical context e.g. instruments to aid in surgical training. The second part will focus on the deep learning for context awareness, in which context-aware system framework ensure robust perception capabilities to intepret surgical processes. The applications to be presented are in the area of percutaneous surgery and robot-assisted kidney surgery.
-"The evaluation  of surgical skills is usually based on observation which is limited both by the need for experts to be present and by the subjectivity of the examiner. The position of instruments or physiological measures recorded during a surgical procedure might be helpful to go beyond the subjectivity of the expert’s supervision. The goal of this study is to obtain unbiased, quantifiable and reproductible metrics to assess surgical skills.
+**December 05, 2017 : Presentation of my thesis and the state of progress** \\
+  * **Speaker:** Gurvan Lecuyer\\
+  * **Sumarry:** Presentation of my thesis subject: "Methods to facilitate the learning steps of recognition algorithm deep learning-based: application to surgery videos". I will talk about the basis of deep learning and then I will explain the work I made since I began, finally I will detail what I'm going to do for the 2 remaining years
-As the internship has ended and the PhD starts I will be presenting what has already been done, how I plan to organise my work as well as what I have learned during the internship that will benefit me for the completion of this project."
+**December 05, 2017 : Presentation and administrative points about ordering and mission procedures** \\
+  * **Speaker:** Noémie Buisard\\
+  * **Sumarry:** Noémie Buisard will quickly present her role in the lab and address some administrative points about ordering and mission procedures. These points will only concern the MediCIS team.
-===== Mardi 9 octobre 2018 13:00-14:00 =====
+**November 13, 2017 : Knowledge-based support for surgical workflow analysis and recognition** \\
+  * **Speaker:** Olga Dergachyova\\
+  * **Sumarry:** Computer assistance became indispensable part of modern surgical procedures. Desire of creating new generation of intelligent operating rooms incited researchers to explore problems of automatic perception and understanding of surgical situations. Situation awareness includes automatic recognition of surgical workflow. A great progress was achieved in recognition of surgical phases and gestures. Yet, there is still a blank between these two granularity levels in the hierarchy of surgical process. Very few research is focused on surgical activities carrying important semantic information vital for situation understanding. Two important factors impede the progress. First, automatic recognition and prediction of surgical activities is a highly challenging task due to short duration of activities, their great number and a very complex workflow with multitude of possible execution and sequencing ways. Secondly, very limited amount of clinical data provides not enough information for successful learning and accurate recognition. In our opinion, before recognizing surgical activities a careful analysis of elements that compose activity is necessary in order to chose right signals and sensors that will facilitate recognition. We used a deep learning approach to assess the impact of different semantic elements of activity on its recognition. Through an in-depth study we determined a minimal set of elements sufficient for an accurate recognition. Information about operated anatomical structure and surgical instrument was shown to be the most important. We also addressed the problem of data deficiency proposing methods for transfer of knowledge from other domains or surgeries. The methods of word embedding and transfer learning were proposed. They demonstrated their effectiveness on the task of next activity prediction offering 22% increase in accuracy. In addition, pertinent observations about the surgical practice were made during the study. In this work, we also addressed the problem of insufficient and improper validation of recognition methods. We proposed new validation metrics and approaches for assessing the performance that connect methods to targeted applications and better characterize capacities of themethod. The work described in this these aims at clearing obstacles blocking the progress of the domain and proposes a new perspective on the problem of surgical workflow recognition
-==== "The use of virtual reality for non-technical skills." ====
+**November 07, 2017 : A Semantic Repository for Medical Data Storage** \\
-Présenté par : Marie-Stephanie Bracq
+  * **Speaker:** Marine Brenet\\
+  * **Sumarry:** For a European research project about radioactivity exposure we need to store and manage images and datas from medical examination from dozens of laboratories. My task is to build a semantic repository for store all datas and allow powerful querying for access to datas with different filters and user friendly for all scientists involved in the project. This semantic repository could be reused for others projects (Biobank, medical datas storage..).  I will introduce myself, how I am building the semantic repository and briefly how I will build a user friendly request software.
-I will present my work on the evaluation of scrub nurses' non-technical skills in a virtual environment. More specifically, I will present the results of my first study on the acceptability of the virtual training environment by experts (scrub nurses from the neurosurgery department of the University Hospital) as well as by non-experts (some of whom are lab members). I will then adress the next steps with the "operating room of errors" scenario, which is currently being finalised, and finally with the very rapid evocation of a scenario on communication currently being developed.
+**October 18, 2017 : Surgical Process Modeling using Hierarchical Task Representations** \\
+  * **Speaker:** Prs. Roy Eagleson and Sandrine De Ribeaupierre from Western University London Ontario\\
-===== Mardi 25 Septembre 2018 13:00-14:00 =====
+**October 10, 2017 : Generic Surgical Process Model Derivation using Test and Flip Net Synthesis** \\
+  * **Speaker:** Aurélien Lamercerie\\
+  * **Sumarry:** There is a constant demand for computer tools to assist the management and conduct of surgical operation. Formal modeling of surgical practices is needed to facilitate the development of these tools. This justifies the need for surgical process model (SPM), based on semantics. One of the difficulties is to construct a generic model, which is not just the composition of somes instances. Our proposal is an innovative approach to deriving a generic model (gSPM) from a somes instances of surgical process model (iSPM). This approach uses a net synthesis method based on the theory of regions. This technique generates a Test 'n Flip net and makes it possible to generalize the variability found in the instances by adding transitions absent from the original data. We have experimented with our proposal on some cases of study with real data. These experiments validated the approach: we arrive at constructing a generic model with interesting levels of generalization. In addition, this work is part of the S3PM / Sunset project, which aims to develop a virtual reality training environment for the surgical process. The virtual reality environment requires a scenario corresponding to the model of the targeted surgical process. This expected scenario can be obtained by adapting the synthesis of the Test 'n Flip net and thus automatically constructing the scenario from somes examples of the target process.
-==== "Special Noon Sharing : 90 to 120 seconds to pitch a crazy idea." ====
+**June 06, 2017 : Automatic Technical Surgical Skill Scoring from Motion Data** \\
-Présenté par : Tout le laboratoire
+  * **Speaker:** Chantal Julliard\\
-===== Vendredi 29 juin 2018 14:00-15:00 =====
+**May 16, 2017 : A Mixed-Reality Surgical Trainer of Laser Fetal Minimally Invasive Surgery for Evaluating Novel Technology** \\
+  * **Speaker:** Allan Javaux, de l'Université de Leuven (Bruxelles, Belgique)\\
+  * **Sumarry:** Fetal surgery is considered one of the most challenging disciplines within Minimally Invasive Surgery (MIS). Indeed, fragility of the anatomic features, the poor visibility, the limited maneuverability and the extreme requirements in terms of instrument handling and positioning precision contribute to this factor. In order to assist the surgeons for a specific laser surgery treatment Twin-Twin Transfusion Syndrome (TTTS), our team is developing (would remove smart) flexible instruments and dedicated techniques for robotic assistance. To evaluate these novel technologies in an early stage of the design, a mixed-reality surgical simulator was developed. Before making too strong conclusions about the technology under evaluation, the simulator must first be validated. Validity based on qualitative data, such as Face and Content Validity, has already been confirmed. However, the validation based on quantitative data, specifically instrument motions, is still undergoing. Through collaboration with Rennes we hope to come up with a mature and sound manner to accomplish a validation based on quantitative data.
-==== "Goals, guidelines, and best practices: a framework for designing augmented reality ultrasound guidance systems; or if you build it, will they come?!" ====
+**April 06, 2017 : Finding the needle in the haystack: detection, tracking and registration in biomedical imaging** \\
-Présenté par : Golafsoun Ameri
+  * **Speaker:** Raphael Sznitman, head of the Ophthalmic Technology Laboratory (ARTORG Center, University of Bern, Switzerland)\\
+  * **Sumarry:** From centimeter-sized observations visible in endoscopy to nanometer large intra-cellular structures discernible with Electron Microscopes, searching and locating objects of interest in images is a central problem in medical image computing. If anything, the need for efficient object detection techniques has never been higher due to the advent of cheaper and ever more sophisticated imaging devices, able of amassing unprecedented quantities of data. And while established search paradigms are showing their limits, faster methods capable of dealing with larger quantities of data are now indispensable. In this talk, I will present a computational framework for object detection with efficiency at its core. This framework, a Bayesian formulation of the traditional “twenty questions” game, considers a sequential strategy for evaluating different parts of the image data in order to locate the object effectively. In this context, we will see how dynamic programming and information theory can be used to characterize a provably-optimal search strategy that is both simple to compute and greedy in nature. Using these results, I will then show how this framework can be used to solve traditional object detection and tracking problems, as well as non-rigid registration of multimodal multi-scale image data, allowing for more accurate solutions and large problems to be tackled.
-Real-time ultrasound has become a crucial aspect of several image-guided interventions. One of the main constraints of such an approach is the difficulty in interpretability of the limited field of view of the image, a problem that has recently been addressed using mixed reality environments, such as augmented reality (AR). The growing popularity and maturity of AR has led to a series of informal guidelines to direct development of new systems and to facilitate regulatory approval. However, the goals of AR image guidance systems and the guidelines for their development have not been thoroughly discussed. The purpose of this talk is to identify the goals, guidelines, and best practices for the development of AR ultrasound guidance and encourage discussion on the effective development of such systems.
+**March 28, 2017 : Overview over image guided interventions and related applications in Trondheim** \\
+  * **Speaker:** Ingerid Reinertsen, senior research scientist from SINTEF (Trondheim, Norway)\\
+  * **Sumarry:** The presentation will focus on image guided interventions in the context of neurosurgery, laparascopic surgery, bronchoscopy and anaesthesiology. Related topics are software development, image processing and machine learning applications.
-===== Jeudi 28 juin 2018 13:00-14:00 =====
+**March 14, 2017 : Ingénierie des Ontologies Formelles: Les Vices et les Vertus** \\
+  * **Speaker:** Bernard Gibaud\\
+  * **Sumarry:** La présentation originale a été faite par Stefan Schulz (Graz, Autriche) durant les Journées Françaises sur les ontologies octobre dernier.  Lien vers la présentation : http://user.medunigraz.at/stefan.schulz/presentations/2016_Ontologies_Formelles_Vices_et_Vertus.pptx Lien vers le site de l'auteur : http://user.medunigraz.at/stefan.schulz/
-==== "Analysis of surgical skills using physiological signals." ====
+**March 07, 2017 : Les enjeux de l'intelligence artificielle** \\
-Présenté par : Thibaut Dognon
+  * **Speaker:** Discussion entre les membres de l'équipe\\
-With the increasing number of surgical procedures performed every year, the precise evaluation of surgical skills is crucial. This evaluation usually consists in a trainee performing a specific task and an examiner evaluating the quality of the procedure with a standardized score (NOTSS, GOALS, OSATS, etc.). This approach is limited both by the need for experts to be present and by the subjectivity of the examiner. Information taken from the position of instruments or physiological measures might be helpful to go beyond the subjectivity of the expert’s supervision. EEG signals have already been used to predict the performance of subjects during the training of sports-related skills. They have also been used to monitor the training improvements in a motor task or visuomotor sequence learning. Using machine or deep learning approaches and complex features from the EEG signals both in sensor and source space, this study aims at obtaining unbiased, quantifiable and reproductible metrics to assess surgical skills.
+**February 28, 2017 : Recognition of Low-Level Surgical Activities is Possible: a Smart Choice of Sensors is the Key!** \\
+  * **Speaker:** Olga Dergachyova\\
+  * **Sumarry:** The present work aims at discovering which sensors and signals would facilitate recognition of low-level surgical activities, usually represented by the following elements: verb describing a performed action, surgical instrument and operated anatomical structure. We hypothesized that activity recognition does not require sensors for all three elements. We conducted a large-scale study using deep learning on semantic data of 154 interventions from four different surgical procedures. The results showed that the instrument and the verb encode similar information. Thus, only one is needed to be tracked, preferably the instrument. The anatomical structure provides some unique cues. Thereby, a sensor capturing it is indispensable. For all studied procedures, a combination of two elements, one being the structure, is sufficient to confidently recognize activity. To the best of our knowledge, this is the first study examining the importance of input signals and information to the process of low-level surgical activity recognition.
-===== Mardi 12 juin 2018 13:00-14:00 =====
+**January 10, 2017 : Semantic Surgical Workflows** \\
+  * **Speaker:** Javier Rojas Balderrama\\
-==== "Sequential surgical signatures in micro-suturing task." ====
-Présenté par : Arnaud Huaulmé
-Surgical processes are generally only studied by identifying differences in populations such as participants or level of expertise. But the similarity between populations is also important in understanding the process. We therefore proposed to study these two aspects. In this presentation, we will demonstrate the concept of sequential surgical signature thank to a pattern mining method applied to a micro-surgical suturing task data set.
+===== 2016 =====
+**December 15, 2016 : Thesis pre-defence: Détection automatique de déviations chirurgicales et identification de comportements chirurgicaux par modélisation et analyse des processus chirurgicaux** \\
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Les événements indésirables (EIs) sont devenus une vraie préoccupation du monde médical, leur réduction étant recherchée pour assurer la meilleure sécurité possible pour les patients. Les événements indésirables sont, selon la HAS, ‘‘des situations qui s'écartent de procédures ou de résultats escomptés dans une situation habituelle et qui sont ou qui seraient potentiellement sources de dommages’’. Alors que les événements indésirables postopératoires sont étudiés depuis de nombreuses années, ceux ayant lieu au cours des opérations ne le sont que depuis récemment, comme le montre la récente classification des événements indésirables intraopératoires par Kaafarani et al. publiée en 2014. Cependant, la classification d'événements indésirables intraopératoires n'est que la première étape pour comprendre les comportements chirurgicaux qui les entraînent. Dans cette thèse, nous présenterons des méthodes pour détecter l'apparition de déviations dues à l'apparition d'événements indésirables intraopératoires et pour identifier des comportements chirurgicaux à partir de modèle de processus chirurgicaux.
-===== Jeudi 7 juin 2018 13:00-14:00 =====
+**December 06, 2016 : Modelling and learning surgical gestures for man-machine collaborative trainin** \\
+  * **Speaker:** Chantal Julliard\\
-==== "Electroencephalography Source Connectivity: Aiming for High Resolution of Brain Networks in Time and Space." ====
+**November 29, 2016 : UHF MRI for stereotactic surgery** \\
-Présenté par : Mahmoud Hassan
+  * **Speaker:** Jonathan C. Lau, MD, Neurosurgery Resident at Western University (London, Canada)\\
+  * **Sumarry:** We are pleased to receive Jonathan C. Lau, MD visiting Rennes. Having a background in Computer Science and Biomedical Engineering, Jonathan is an active collaborator with the VASST laboratory of Terry Peters. His current research goals are to develop and validate image processing software for neurosurgical applications to facilitate improved characterization of neurosurgical illnesses using computational modeling techniques and the development of a framework for improved surgical planning and intra-operative neuronavigation.
-The human brain is a large-scale network the function of which depends on dynamic interactions between spatially distributed regions. In the rapidly evolving field of network neuroscience, two unresolved challenges hold the promise of potential breakthroughs. First, functional brain networks should be identified using noninvasive and easy-to-use neuroimaging techniques. Second, the time-space resolution of these techniques should be good enough to assess the dynamics of the identified networks. Emerging evidence suggests that the electroencephalography (EEG) source-connectivity method may offer solutions to both issues, provided that scalp EEG signals are appropriately processed. Therefore, this technique's performance strongly depends on signal processing that involves various methods, such as preprocessing approaches, inverse solutions, statistical couplings between signals, and network science.
+**November 17, 2016 : Measuring the acceptance of S3PM by scrub nurses** \\
+  * **Speaker:** Marie-Stéphanie Bracq\\
+  * **Sumarry:** Marie-Stéphanie Bracq is a newcomer PhD student preparing a thesis in collaboration of CRPCC (Psychology Research Center, Cognition and Communication, University of Rennes 2) and MediCIS team, co-directed by Pierre Jannin and Estelle Michinov. Her thesis is about the assessment of scrub nurses non-technical skills in a collaborative learning virtual environment. Her PhD work lies in the context of SUNSET project (Scrub Nurse Non-Technical Skills Training System) which is the continuation of S3PM project (Synthesis and Simulation of Surgical Process Models). The objective of her current work is to measure acceptance of S3PM virtual environment by surgical scrub nurses before deploying it for training. Marie-Stéphanie will make a presentation introducing her thesis. The title of her talk is "Measuring the acceptance of S3PM by scrub nurses". The idea of measuring the acceptance of the proposed training technology is to be able to predict its use intentions and understand possible brakes stopping from its application. She will also present 2 models: 1) TAM: Technology Acceptance Model by Dabis (1989), and 2) UTAUT: Unified Theory of Acceptance and Use of Technology by Vankatesh (2003, 2012), as well as inqueries used for expiriments with S3PM.
-===== Jeudi 31 mai 2018 13:00-14:00 =====
+**November 15, 2016 : Intelligent surgical robotic system based on the multidisciplinary computational anatomy** \\
+  * **Speaker:** Professeur Makoto Hashizume (Université de Kyushu, Japon)\\
+  * **Sumarry:** Nous avons le plaisir d'accueillir le Professeur Hashizume de l'Université de Kyushu. Il nous présentera la partie robotique d'un énorme projet national qui regroupe toutes les principales équipes de recherche japonaises de notre domaine, projet dont il est le porteur.
-==== "Special Noon Sharing: Your work in 90 seconds." ====
+**November 08, 2016 : Angiogram Image Processing for Catheter Guidance in Thoracoabdominal Region** \\
-Présenté par : Tout le laboratoire.
+  * **Speaker:** Professor Hideaki Haneishi (Center for Frontier Medical Engineering, Chiba University, Japan)\\
+  * **Sumarry:** Interventional radiology (IVR) with catheter is a useful, less invasive procedure for diagnosis and treatment of diseases in thoracoabdominal organs such as liver. However, such organs are always moving due to respiration, which makes the catheter operation difficult. Patients breath holding is a solution but some patients including elder people sometimes cannot hold the breath. Image processing for visualizing high contrast vessel pattern without breath holding is highly desired in this field. Digital subtract angiography (DSA) is one of imaging methods using X-ray image and is commonly conducted to clearly visualize the vessels during intervention with a catheter. But DSA requires breath-holding. Thus, non-breath-hold DSA is very attractive.
-===== Jeudi 17 et jeudi 24 mai 2018 13:00-14:00 =====
+{{:brainstorming:20161108_131356-02.jpeg |}}
-==== "Interaction in medical image segmentation." ====
-Présenté par : John Baxter
-__Interaction in medical image segmentation:__
-Human-computer interaction as a tool-kit is diverse but also infrequently used to provide the context behind movements in computer science. New developments in hardware and algorithms tend to take precedence in explaining these advancements more so than an understanding of how they are actually used. The goal of this set of presentations is to introduce concepts from human-computer interaction and how it applies to segmentation programs in order to help spur a more out-of-the-box thought process to a familiar topic.
-__Part 1: Olabarragia & Smeulders, “Interaction in the segmentation of medical images: a survey”, (2001)__
-After introducing concepts from HCI, we will explore the first major work in understanding medical image segmentation (and ultimately medical image processing in general) from the perspective of human-computer interaction written by Olabarragia & Smeulders in 2001 for Medical Image Analysis. At this point in the development of segmentation algorithms, many of the most common interaction mechanisms have both been developed and were also about to be developed, making this article a particularly good snapshot into understanding what goes into developing a philosophical framework to understand a complex computational process.
-__Part 2: Baxter et al., “The Semiotics of Medical Image Segmentation”, (2017)__
-My review paper, written in 2017 for Medical Image Analysis, is largely a response to that of Olabarragia & Smeulders. Specifically, this paper proposes a framework that explains Olabarragia & Smeulders’ concluisions while at the same time being more rigorously justified in order to be applicable for a longer span of time. The framework is built on the idea that segmentation can be understood as an exchange of information between a human and a computer, mediated by signs, and applying semiotics and cognitive science to this understanding can give us a rubric as to how to analyze and improve these signs.
-===== Mardi 3 avril 2018 13:00-14:00 =====
-==== "Festivals de printemps et d'été à Rennes et autour." ====
-Présenté par : Gurvan Lecuyer
-My presentation is about the main music festivals of the spring and summer in Rennes, Brittany and around. The purpose of this presentation is to introduce newcomers to this incredible occasion to have fun while listening good music. I will present the lineup of each festivals and the experience you can expect for those I've attended.
-===== Mardi 27 mars 2018 13:00-14:00 =====
-==== "Presentation of the differents ongoing projects of MediCIS." ====
-Présenté par : Pierre JANNIN
-===== Mardi 20 mars 2018 13:00-14:00 =====
-==== "Presentation of the "Délégation à la Recherche Clinique et à l'Innovation (DRCI)"." ====
-Présenté par : Loïc FIN
-===== Lundi 12 mars 2018 13:00-14:00 =====
-==== "Simulation, performance and human factors in obstetrics and gynecology." ====
-Présenté par : Maela LE LOUS
-===== Mardi 20 février 2018 13:00-14:00 =====
-==== "Exploring Fusion Models in Computer Vision for Medical Image Computing (part 2)." ====
-Présenté par : Duygu Sarikaya
-===== Mardi 13 février 2018 13:00-14:00 =====
-==== "Exploring Fusion Models in Computer Vision for Medical Image Computing." ====
-Présenté par : Duygu Sarikaya
-Automatic understanding of medical images has been an active research area, as a need for universally accepted, standard and validated metrics is addressed in the community.  The recent advances of computer vision and machine learning algorithms coupled with the use of digital imaging modalities has led to improvements in automatic understanding of medical imaging data. In this talk, we explore fusion models in computer vision for medical image computing. We propose solutions to the open problems of robot-assisted surgery (RAS) video understanding, and segmentation of the tumor and anatomical structures of the brain. Modeling the gestures and skill level of surgeons in robot-assisted surgery (RAS) videos presents an interesting problem. Early identification of technical competence in surgical skills is expected to help tailor training to personalized needs of surgeons in training. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. Characterization of anatomical structure of the brain in magnetic resonance human brain images (MRI) has also gained high interest in recent years. There is a strong need for a computer-aided system that will automatically and accurately define the tumor and anatomical structures of the brain. A universally-accepted, standardized automatic mapping and segmentation of brain volumetry would be a significant improvement for diagnosis, modeling personalized progression, and treatment monitoring of neurologic conditions. We show that exploiting the relationship across different tasks, jointly reasoning multi-tasks, and taking advantage of a combination of shared and task-specific representations, or using smart fusion of a priori knowledge inferred from multiple data sources for these problems perform astonishingly better than their single-task counterparts.
-===== Mardi 6 février 2018 13:00-14:00 =====
-==== "Study of anatomo-clinical correlation in Deep Brain Stimulation by Machine Learning: A presentation of my thesis." ====
-Présenté par : Maxime Peralta
-Deep Brain Stimulation (DBS) is a surgical procedure used notably for conteract the motor effects of Parkinson Desease. Even though it shows promising results, several unknowns and difficulties remain. Artifical intelligence, through Machine Learning (ML) or Deep Learning (DL), is forseen to be one of the solution to come up with these issues.
-During this presentation, i will quickly introduce DBS and ML/DL. After that, i will present the objectives of my thesis by talking about the difficulties of using deep learning algorithms in neurosurgery and introducing tractography. I'll then present a study in progress with Clément Baumgarten and finish by introducing the objectives of my next study.
-===== Mardi 30 janvier 2018 13:00-14:00 =====
-==== "Relationships between Expertise, Team Familiarity and Surgical Workflow Disruptions: an Observational Study." ====
-Présenté par : Pierre-Louis Henaux
-A workflow disruption (WD) is characterized by deviations from the natural progression of an operation, thus possibly compromising operation safety. Disruptions in the operating room (OR) can be subdivided into communication, usability, physical layout, environmental hazards, general interruptions and equipment failures. Communication failures in the OR can occur in approximately 30% of team exchanges and a third of these causes of WD endanger patient safety. Surgical errors are strongly related to number of WD.
-Teamwork has been shown as an essential factor to reduce WD. Research in other high-risk settings such as in aviation field highlighted the fact that limited team familiarity (TF) between teammates can lead to negative safety outcomes. The aim of this exploratory study was to examine the relationships between expertise, TF and WD with scrub nurses (SN) and neurosurgeons through an observation of elective neurosurgical procedures carried out by surgeons and SN with different levels of expertise and different degrees of familiarity with each other.
-===== Mardi 23 janvier 2018 13:00-14:00 =====
-==== "Skill based assistance in robotic surgery." ====
-Présenté par : Atsushi Nakazawa
-Robotic surgery has gained increasing popularity in recent years. Intelligent robotic surgical assistance in surgical sub-tasks such as suturing has the potential to enhance surgeon's performance and reduce fatigue and operating time. Previous works in surgical automation use a replication of demonstrated motions or a planned path, but they are not necessarily skilled motions. Therefore, we aim to develop an assistance system in robotic surgery based on skill analysis. As a first step, we are working on environment recognition to get better understanding of the skills.
-===== Mardi 9 janvier 2018 13:00-14:00 =====
-==== "Mental Representation during Preoperative Surgical Planning." ====
-Présenté par : Pierre-Louis Henaux
-Expert judgment is vital for safe surgery.  Judgment is difficult to define. A critical aspect of it is the ability of accurately mentally represent the purpose of surgical procedure.  Mental Representation (MR) determines the details of this procedure, plans what decisions would be made, as well as what approaches would be taken and whether a procedure fits within a surgeon confort zone.  Therefore, MR is critical to our understanding of surgical expertise. There is a body of literature about decision making, surgical intuition, clinical reasoning, problems solving. However, we should understand the essence of all these non-technical skills. MR is a process which underpins all these cognitive skills. Through a qualitative study following a constructivist grounded theory methodology, the aim of this study was to explore how does the surgeon mentally represent the operative procedure preoperatively and how this MR changes over time with development of surgical expertise.
-===== Mardi 19 décembre 2017 13:00-14:00 =====
-==== "Development of an intelligent surgical training system for Thoracentesis." ====
-Présenté par : Hiren Nakawala
-Surgical training improves patient care, helps to reduce surgical risks, increases surgeon’s confidence, and thus enhances overall patient safety. Current surgical training systems are more focused on developing technical skills, e.g. dexterity, of the surgeons while lacking the aspects of context-awareness and intra-operative real-time guidance. Context-aware intelligent training systems interpret the current surgical situation and help surgeons to train on surgical tasks. first part of the talk will introduce context-aware system framework which helps to identify surgical context e.g. instruments to aid in surgical training. The second part will focus on the deep learning for context awareness, in which context-aware system framework ensure robust perception capabilities to intepret surgical processes. The applications to be presented are in the area of percutaneous surgery and robot-assisted kidney surgery.
-===== Mardi 5 décembre 2017 13:00-13:30 =====
-==== "Presentation of my thesis and the state of progress." ====
-Présenté par : Gurvan Lecuyer
-Presentation of my thesis subject: "Methods to facilitate the learning steps of recognition algorithm deep learning-based: application to surgery videos". I will talk about the basis of deep learning and then I will explain the work I made since I began, finally I will detail what I'm going to do for the 2 remaining years
-===== Mardi 5 décembre 2017 13:30-14:00 =====
-==== "Presentation and administrative points about ordering and mission procedures." ====
-Présenté par : Noémie Buisard
-Noémie Buisard will quickly present her role in the lab and address some administrative points about ordering and mission procedures. These points will only concern the MediCIS team.
-===== Lundi 13 novembre 2017 13:00-14:00 =====
-==== "Knowledge-based support for surgical workflow analysis and recognition." ====
-Présenté par : Olga Dergachyova
-Computer assistance became indispensable part of modern surgical procedures. Desire of creating new generation of intelligent operating rooms incited researchers to explore problems of automatic perception and understanding of surgical situations. Situation awareness includes automatic recognition of surgical workflow. A great progress was achieved in recognition of surgical phases and gestures. Yet, there is still a blank between these two granularity levels in the hierarchy of surgical process. Very few research is focused on surgical activities carrying important semantic information vital for situation understanding. Two important factors impede the progress. First, automatic recognition and prediction of surgical activities is a highly challenging task due to short duration of activities, their great number and a very complex workflow with multitude of possible execution and sequencing ways. Secondly, very limited amount of clinical data provides not enough information for successful learning and accurate recognition.
-In our opinion, before recognizing surgical activities a careful analysis of elements that compose activity is necessary
-in order to chose right signals and sensors that will facilitate recognition. We used a deep learning approach to assess the impact of different semantic elements of activity on its recognition. Through an in-depth study we determined a minimal set of elements sufficient for an accurate recognition. Information about operated anatomical structure and surgical instrument was shown to be the most important. We also addressed the problem of data deficiency proposing methods for transfer of knowledge from other domains or surgeries. The methods of word embedding and transfer learning were proposed. They demonstrated their effectiveness on the task of next activity prediction offering 22% increase in accuracy. In addition, pertinent observations about the surgical practice were made during the study. In this work, we also addressed the problem of insufficient and improper validation of recognition methods. We proposed new validation metrics and approaches for assessing the performance that connect methods to targeted applications and better characterize capacities of themethod. The work described in this these aims at clearing obstacles blocking the progress of the domain and proposes a new perspective on the problem of surgical workflow recognition.
-===== Mardi 7 novembre 2017 13:00-14:00 =====
-==== "A Semantic Repository for Medical Data Storage" ====
-Présenté par : Marine Brenet
-For a European research project about radioactivity exposure we need to store and manage images and datas from medical examination from dozens of laboratories. My task is to build a semantic repository for store all datas and allow powerful querying for access to datas with different filters and user friendly for all scientists involved in the project. This semantic repository could be reused for others projects (Biobank, medical datas storage..).
-I will introduce myself, how I am building the semantic repository and briefly how I will build a user friendly request software.
-===== Mercredi 18 octobre 2017 14:00-15:00 =====
-==== "Surgical Process Modeling using Hierarchical Task Representations" ====
-Présenté par : Prs. Roy Eagleson and Sandrine De Ribeaupierre from Western University London Ontario
-===== Mardi 10 octobre 2017 13:00-14:00 =====
-==== "Generic Surgical Process Model Derivation using Test and Flip Net Synthesis" ====
-Présenté par : Aurélien Lamercerie
-There is a constant demand for computer tools to assist the management and conduct of surgical operation. Formal modeling of surgical practices is needed to facilitate the development of these tools. This justifies the need for surgical process model (SPM), based on semantics. One of the difficulties is to construct a generic model, which is not just the composition of somes instances.
-Our proposal is an innovative approach to deriving a generic model (gSPM) from a somes instances of surgical process model (iSPM). This approach uses a net synthesis method based on the theory of regions. This technique generates a Test 'n Flip net and makes it possible to generalize the variability found in the instances by adding transitions absent from the original data.
-We have experimented with our proposal on some cases of study with real data. These experiments validated the approach: we arrive at constructing a generic model with interesting levels of generalization.
-In addition, this work is part of the S3PM / Sunset project, which aims to develop a virtual reality training environment for the surgical process. The virtual reality environment requires a scenario corresponding to the model of the targeted surgical process. This expected scenario can be obtained by adapting the synthesis of the Test 'n Flip net and thus automatically constructing the scenario from somes examples of the target process.
-===== Mardi 6 juin 2017 13:00-14:00 =====
-==== "Automatic Technical Surgical Skill Scoring from Motion Data" ====
-Présenté par : Chantal Julliard
-===== Mardi 16 mai 2017 13:00-14:00 =====
-==== "A Mixed-Reality Surgical Trainer of Laser Fetal Minimally Invasive Surgery for Evaluating Novel Technology" ====
-Présenté par : Allan Javaux, de l'Université de Leuven (Bruxelles, Belgique)
-Fetal surgery is considered one of the most challenging disciplines within Minimally Invasive Surgery (MIS). Indeed, fragility of the anatomic features, the poor visibility, the limited maneuverability and the extreme requirements in terms of instrument handling and positioning precision contribute to this factor. In order to assist the surgeons for a specific laser surgery treatment Twin-Twin Transfusion Syndrome (TTTS), our team is developing (would remove smart) flexible instruments and dedicated techniques for robotic assistance. To evaluate these novel technologies in an early stage of the design, a mixed-reality surgical simulator was developed. Before making too strong conclusions about the technology under evaluation, the simulator must first be validated. Validity based on qualitative data, such as Face and Content Validity, has already been confirmed. However, the validation based on quantitative data, specifically instrument motions, is still undergoing. Through collaboration with Rennes we hope to come up with a mature and sound manner to accomplish a validation based on quantitative data.
-===== Mardi 6 avril 2017 14:00-15:00 =====
-==== "Finding the needle in the haystack: detection, tracking and registration in biomedical imaging" ====
-Présenté par : Raphael Sznitman, head of the Ophthalmic Technology Laboratory (ARTORG Center, University of Bern, Switzerland)
-From centimeter-sized observations visible in endoscopy to nanometer large intra-cellular structures discernible with Electron Microscopes, searching and locating objects of interest in images is a central problem in medical image computing. If anything, the need for efficient object detection techniques has never been higher due to the advent of cheaper and ever more sophisticated imaging devices, able of amassing unprecedented quantities of data. And while established search paradigms are showing their limits, faster methods capable of dealing with larger quantities of data are now indispensable.
-In this talk, I will present a computational framework for object detection with efficiency at its core. This framework, a Bayesian formulation of the traditional “twenty questions” game, considers a sequential strategy for evaluating different parts of the image data in order to locate the object effectively. In this context, we will see how dynamic programming and information theory can be used to characterize a provably-optimal search strategy that is both simple to compute and greedy in nature. Using these results, I will then show how this framework can be used to solve traditional object detection and tracking problems, as well as non-rigid registration of multimodal multi-scale image data, allowing for more accurate solutions and large problems to be tackled.
-===== Mardi 28 mars 2017 13:00-14:00 =====
-==== "Overview over image guided interventions and related applications in Trondheim" ====
-Présenté par : Ingerid Reinertsen, senior research scientist from SINTEF (Trondheim, Norway)
-The presentation will focus on image guided interventions in the context of neurosurgery, laparascopic surgery, bronchoscopy and anaesthesiology. Related topics are software development, image processing and machine learning applications.
-===== Mardi 14 mars 2017 13:00-14:00 =====
-==== "Ingénierie des Ontologies Formelles: Les Vices et les Vertus" ====
-Présenté par : [[:members:bernard.gibaud:index| Bernard Gibaud]]
-La présentation originale a été faite par Stefan Schulz (Graz, Autriche) durant les Journées Françaises sur les ontologies octobre dernier.
-Lien vers la présentation : http://user.medunigraz.at/stefan.schulz/presentations/2016_Ontologies_Formelles_Vices_et_Vertus.pptx
-Lien vers le site de l'auteur : http://user.medunigraz.at/stefan.schulz/
-===== Mardi 7 mars 2017 13:00-14:00 =====
-==== "Les enjeux de l'intelligence artificielle" ====
-Discussion entre les membres de l'équipe
-===== Mardi 28 février 2017 13:00-14:00 =====
-==== "Recognition of Low-Level Surgical Activities is Possible: a Smart Choice of Sensors is the Key!" ====
-Présenté par : [[:members:olga.dergachyova:index| Olga Dergachyova]]
-The present work aims at discovering which sensors and signals would facilitate recognition of low-level surgical activities, usually represented by the following elements: verb describing a performed action, surgical instrument and operated anatomical structure. We hypothesized that activity recognition does not require sensors for all three elements. We conducted a large-scale study using deep learning on semantic data of 154 interventions from four different surgical procedures. The
-results showed that the instrument and the verb encode similar information. Thus, only one is needed to be tracked, preferably the instrument. The anatomical structure provides some unique cues. Thereby, a sensor capturing it is indispensable. For all studied procedures, a combination of two elements, one being the structure, is sufficient to confidently recognize activity. To the best of our knowledge, this is the first study examining the importance of input signals and information to the process
-of low-level surgical activity recognition.
-===== Mardi 10 janvier 2017 13:00-14:00 =====
-==== "Semantic Surgical Workflows" ====
-Présenté par : Javier Rojas Balderrama, PhD
-===== Jeudi 15 décembre 2016 13:00-14:00 =====
-==== "Détection automatique de déviations chirurgicales et identification de comportements chirurgicaux par modélisation et analyse des processus chirurgicaux" ====
-Présenté par : Arnaud Huaulmé
-Les événements indésirables (EIs) sont devenus une vraie préoccupation du monde médical, leur réduction étant recherchée pour assurer la meilleure sécurité possible pour les patients. Les événements indésirables sont, selon la HAS, ‘‘des situations qui s'écartent de procédures ou de résultats escomptés dans une situation habituelle et qui sont ou qui seraient potentiellement sources de dommages’’. Alors que les événements indésirables postopératoires sont étudiés depuis de nombreuses années, ceux ayant lieu au cours des opérations ne le sont que depuis récemment, comme le montre la récente classification des événements indésirables intraopératoires par Kaafarani et al. publiée en 2014. Cependant, la classification d'événements indésirables intraopératoires n'est que la première étape pour comprendre les comportements chirurgicaux qui les entraînent.
-Dans cette thèse, nous présenterons des méthodes pour détecter l'apparition de déviations dues à l'apparition d'événements indésirables intraopératoires et pour identifier des comportements chirurgicaux à partir de modèle de processus chirurgicaux.
-Ce travail a nécessité de concevoir et développer une modélisation formelle de la rectopexie et des événements indésirables qui sont associés à cette procédure chirurgicale grâce à la mise en place d'ontologies. Cette modélisation formelle nous a permis de bien appréhender le principe de cette opération et de fournir un vocabulaire permettant une annotation détaillée de vidéos endoscopiques de rectopexies, afin de créer des modèles de processus chirurgicaux en jeu.
-Grâce à l'annotation des vidéos chirurgicales basée sur cette modélisation, nous avons développé une méthode de détection automatique des déviations dues à l'apparition d'événements indésirables. Cette méthode est basée sur un alignement temporel non linéaire multidimensionnel, que nous avons développé, suivi d'un modèle semi-Markovien caché que nous avons entraîné pour déterminer s'il existe des déviations par rapport à une chirurgie de référence et si celles-ci sont dues à des événements indésirables.
-Cette détection de déviations dues aux événements indésirables est la première étape afin de comprendre les raisons de leurs apparitions. Nous émettons l'hypothèse que leurs apparitions peuvent être expliquées par une succession d’activités, c'est-à-dire un pattern. Pour répondre à cette hypothèse, nous avons mis en place une méthode de découverte de patterns permettant d'identifier les comportements chirurgicaux spécifiques à différents critères. Cette identification de comportements chirurgicaux est réalisée par une classification ascendante hiérarchique avec la mise en place d'une nouvelle métrique basée sur les patterns partagés entre les chirurgies. Afin de valider notre méthode, nous l'avons comparé à deux études mettant en évidence des différences de comportements chirurgicaux, par exemple entre différents sites chirurgicaux ou entre deux types de procédures de la même opération. Une fois la méthode validée, nous avons utilisé notre méthode afin de montrer s'il existait des comportements chirurgicaux spécifiques à des données préopératoires et à l'apparition d'événements indésirables.
-===== Mardi 6 décembre 2016 13:00-14:00 =====
-==== "Modelling and learning surgical gestures for man-machine collaborative training" ====
-Présenté par : [[:members:chantal.julliard:index| Chantal Julliard]]
-===== Mardi 29 novembre 2016 13:00-14:00 =====
-==== "UHF MRI for stereotactic surgery" ====
-Présenté par : Jonathan C. Lau, MD, Neurosurgery Resident at Western University (London, Canada)
-We are pleased to receive Jonathan C. Lau, MD visiting Rennes. Having a background in Computer Science and Biomedical Engineering, Jonathan is an active collaborator with the VASST laboratory of Terry Peters. His current research goals are to develop and validate image processing software for neurosurgical applications to facilitate improved characterization of neurosurgical illnesses using computational modeling techniques and the development of a framework for improved surgical planning and intra-operative neuronavigation.
-===== Vendredi 17 novembre 2016 15:00-14:00 =====
-==== "Measuring the acceptance of S3PM by scrub nurses" ====
-Présenté par : Marie-Stéphanie Bracq
-Marie-Stéphanie Bracq is a newcomer PhD student preparing a thesis in collaboration of CRPCC (Psychology Research Center, Cognition and Communication, University of Rennes 2) and MediCIS team, co-directed by Pierre Jannin and Estelle Michinov. Her thesis is about the assessment of scrub nurses non-technical skills in a collaborative learning virtual environment. Her PhD work lies in the context of SUNSET project (Scrub Nurse Non-Technical Skills Training System) which is the continuation of S3PM project (Synthesis and Simulation of Surgical Process Models). The objective of her current work is to measure acceptance of S3PM virtual environment by surgical scrub nurses before deploying it for training. Marie-Stéphanie will make a presentation introducing her thesis. The title of her talk is "Measuring the acceptance of S3PM by scrub nurses". The idea of measuring the acceptance of the proposed training technology is to be able to predict its use intentions and understand possible brakes stopping from its application. She will also present 2 models: 1) TAM: Technology Acceptance Model by Dabis (1989), and 2) UTAUT: Unified Theory of Acceptance and Use of Technology by Vankatesh (2003, 2012), as well as inqueries used for expiriments with S3PM.
-===== Mardi 15 novembre 2016 13:00-14:00 =====
-==== "Intelligent surgical robotic system based on the multidisciplinary computational anatomy" ====
-Présenté par : Professeur Makoto Hashizume (Université de Kyushu, Japon)
-Nous avons le plaisir d'accueillir le Professeur Hashizume de l'Université de Kyushu. Il nous présentera la partie robotique d'un énorme projet national qui regroupe toutes les principales équipes de recherche japonaises de notre domaine, projet dont il est le porteur.
-===== Mardi 8 novembre 2016 13:00-14:00 =====
-==== "Angiogram Image Processing for Catheter Guidance in Thoracoabdominal Region" ====
-Présenté par : Professor Hideaki Haneishi (Center for Frontier Medical Engineering, Chiba University, Japan)
-{{:brainstorming:20161108_131356-02.jpeg|}}
-Interventional radiology (IVR) with catheter is a useful, less invasive procedure for diagnosis and treatment of diseases in thoracoabdominal organs such as liver. However, such organs are always moving due to respiration, which makes the catheter operation difficult. Patients breath holding is a solution but some patients including elder people sometimes cannot hold the breath. Image processing for visualizing high contrast vessel pattern without breath holding is highly desired in this field. Digital subtract angiography (DSA) is one of imaging methods using X-ray image and is commonly conducted to clearly visualize the vessels during intervention with a catheter. But DSA requires breath-holding. Thus, non-breath-hold DSA is very attractive.
 Two methods for angiogram image processing are presented for catheter guidance in thoracoabdominal region. One is roadmap generation from angiogram motion picture. The other is respiration-synchronized real-time generation of angiogram from fluoroscopy images. Both methods utilize fluoroscopy and/or angiography motion pictures and generate blood vessel enhanced images to assist physician’s catheter control and guidance of catheter feeding. The first method was tested by 53 patient data and the second method was tested 12 patient data. Through the experiments with patient data, the effectiveness of the proposed methods was confirmed.
@@ Line 743: / Line 759: @@
 In terms of the second method, a respiratory synchronized DSA generation based on a respiratory phase matching is performed. Pre-operative angiographic images under natural respiration and intra-operative fluoroscopic image under natural respiration during the operation are used. For each fluoroscopic image, the proposed method chooses an angiographic image in the most similar respiratory phase by a pattern matching technique in real time. We conducted two kinds of experiments to confirm that the proposed method can be used as the free breathing DSA and the respiratory synchronized roadmap. The result showed that the proposed method can produce fine DSA without breath-holding and the processing can be done in real-time.
+{{ :brainstorming:20161108_131332-02.jpeg|}}
 Respiratory phase matching method was proposed for generation of free breathing DSA. Acceptable fine DSA could be obtained without breath-holding by using proposed method. We also have proposed a blood vessel enhancement method using consecutive angiographic images with respiratory motion and heartbeat. The proposed method is composed of robust principal component analysis and a deformation technique to extract blood vessel pattern from angiographic images. We applied the proposed method to 53 patient data. In most cases we confirmed that artifacts by difference between live images and mask images were reduced by the proposed method.
 As future works for the first method, we will evaluate the clinical value. As future works for the second method we will apply the method to clinical data more and more and obtained feedback from physicians side so that the method will be improved for clinical practice.
-{{:brainstorming:20161108_131332-02.jpeg|}}
-===== Jeudi 17 novembre 2016 14:00-16:00 =====
+**November 17, 2016 : Pré-soutenance de thèse : Imagerie fonctionnelle intraopératoire naviguée pour l'optimisation de la chirurgie des tumeurs cérébrales** \\
-==== "Pré-soutenance de thèse : Imagerie fonctionnelle intraopératoire naviguée pour l'optimisation de la chirurgie des tumeurs cérébrales" ====
+  * **Speaker:** Frederic Monge\\
-Présenté par : [[:members:frederic.monge:index| Frederic Monge]]
+  * **Sumarry:** Les gliomes sont des tumeurs cérébrales primitives représentant le deuxième cancer le plus fréquent chez l’enfant et la troisième cause de mortalité chez l’adulte jeune. Il a été démontré qu’une chirurgie d’exérèse tumorale permet d’augmenter la qualité et la durée de vie du patient, voir même dans certains cas, d’obtenir sa guérison. L’identification intraopératoire des résidus tumoraux permettrait au chirurgien de vérifier, in situ, la qualité de son geste d’exérèse. Une nouvelle modalité d’imagerie intraopératoire a été proposée comme solution pour détecter les tumeurs résiduelles. Elle se base sur l’utilisation d’une sonde nucléaire combinée à un système de localisation optique. Cette nouvelle modalité, appelée imagerie surfacique de positons (ISP), permet la génération d’images de la distribution surfacique d’un radiotraceur comme le 18F d’une zone d’intérêt scannée. L’ISP n’étant actuellement pas utilisée en clinique, nous proposons pour la première fois une étude de faisabilité de son utilisation pour l’optimisation de la chirurgie des tumeurs cérébrales. Nous montrons les limites de l’utilisation potentielle de l’ISP dans un context neurochirurgical par des études expérimentales en considérant des facteurs intraopératoires pouvant influencer la qualité des images générées par le système. Les contributions présentées se concentrent sur trois axes. Dans un premier temps, nous souhaitons obtenir des images fonctionnelles d’ISP avec un temps de calcul faible. L’application de modèles d’acquisition aux mesures permettent d’améliorer la qualité des images, au détriment d’un temps de calcul élevé. Nous suggérons un nouveau modèle d’acquisition dédié au contexte intraopératoire, permettant l’amélioration de la résolution et du contraste des images pour un temps de calcul réduit. Un deuxième axe est dédié à l’étude de l’impact d’une acquisition intraopératoire sur les performances du système. Nous proposons l’estimation des paramètres intrinsèques de la sonde nucléaire utilisée et de l’influence de la hauteur du processus de scan sur leurs valeurs. Le dernier axe est consacré à la validation de modèles d’acquisition dans le contexte intraopératoire. Nous présentons une étude comparative des performances de modèles d’acquisition en considérant l’impact potentiel de la vitesse de scan Durant l’acquisition. L’ensemble de ces travaux a contribué à l’étude de faisabilité de l’utilisation d’un système d’ISP en intraopératoire, proposée pour la première fois en neurochirurgie.
-Les gliomes sont des tumeurs cérébrales primitives représentant le
+**October 25, 2016 : Surgical Vision Augmentation in da Vinci Robotic Prostatectomy** \\
-deuxième cancer le plus fréquent chez l’enfant et la troisième cause de mortalité
+  * **Speaker:** Xiongbiao Luo\\
-chez l’adulte jeune. Il a été démontré qu’une chirurgie d’exérèse tumorale permet
+  * **Sumarry:** Da Vinci robotic prostatectomy that is increasingly performed for minimally invasive prostatic tumor resection uses stereoscopic laparoscopes to intuitively visualize the organ surface in the body and manipulate various surgical tools under the insufficient light sources and the relatively narrow field of view of the binocular stereoscopic laparoscope that usually limits the visualization on the organ being operated on and its anatomical surroundings. Surgical vision augmentation in accordance with non-uniform illumination correction, fast visibility-contrast fusion defogging, motion magnification, and surgical filed 3D reconstruction techniques to maintain and augment a clear field of in-situ direct vision in robotic prostatectomy is paramount not only for safety by preventing inadvertent injury, but also to improve precision and reduce operative time.
-d’augmenter la qualité et la durée de vie du patient, voir même dans certains cas,
-d’obtenir sa guérison. L’identification intraopératoire des résidus tumoraux permettrait
-au chirurgien de vérifier, in situ, la qualité de son geste d’exérèse. Une nouvelle
-modalité d’imagerie intraopératoire a été proposée comme solution pour détecter les
-tumeurs résiduelles. Elle se base sur l’utilisation d’une sonde nucléaire combinée à
-un système de localisation optique. Cette nouvelle modalité, appelée imagerie surfacique
-de positons (ISP), permet la génération d’images de la distribution surfacique
-d’un radiotraceur comme le 18F d’une zone d’intérêt scannée. L’ISP n’étant
-actuellement pas utilisée en clinique, nous proposons pour la première fois une étude
-de faisabilité de son utilisation pour l’optimisation de la chirurgie des tumeurs cérébrales.
-Nous montrons les limites de l’utilisation potentielle de l’ISP dans un contexte
-neurochirurgical par des études expérimentales en considérant des facteurs intraopératoires
-pouvant influencer la qualité des images générées par le système. Les
-contributions présentées se concentrent sur trois axes. Dans un premier temps, nous
-souhaitons obtenir des images fonctionnelles d’ISP avec un temps de calcul faible.
-L’application de modèles d’acquisition aux mesures permettent d’améliorer la qualité
-des images, au détriment d’un temps de calcul élevé. Nous suggérons un nouveau
-modèle d’acquisition dédié au contexte intraopératoire, permettant l’amélioration de
-la résolution et du contraste des images pour un temps de calcul réduit. Un deuxième
-axe est dédié à l’étude de l’impact d’une acquisition intraopératoire sur les performances
-du système. Nous proposons l’estimation des paramètres intrinsèques de la
-sonde nucléaire utilisée et de l’influence de la hauteur du processus de scan sur leurs
-valeurs. Le dernier axe est consacré à la validation de modèles d’acquisition dans le
-contexte intraopératoire. Nous présentons une étude comparative des performances
-de modèles d’acquisition en considérant l’impact potentiel de la vitesse de scan durant
-l’acquisition. L’ensemble de ces travaux a contribué à l’étude de faisabilité de
-l’utilisation d’un système d’ISP en intraopératoire, proposée pour la première fois
-en neurochirurgie.
-===== Mardi 25 octobre 2016 13:00-14:00 =====
+**September 27, 2016 : Séquencement d'actions en environnement virtuel collaboratif** \\
-==== "Surgical Vision Augmentation in da Vinci Robotic Prostatectomy" ====
+  * **Speaker:** Guillaume Claude\\
-Présenté par : Xiongbiao Luo
+  * **Sumarry:** Un environnement virtuel interactif à lui seul ne permet pas de répondre à tous les besoins liés à son utilisation. Dans le cadre de la formation par Réalité Virtuelle, un cadrage de l’activité de l’apprenant est important pour offrir une formation efficace. Le problème est le même dans les fictions interactives : seul, l’environnement n’offre qu’un intérêt limité. Nous nous intéressons ici au problème de la spécification du séquencement des actions dans un environnement  collaboratif. Il s’agit de définir puis de contrôler ce qui peut ou doit se passer au cours de la simulation dans un contexte potentiellement multiutilisateur. Ceci passe, entre autres, par la spécification (puis l’exécution) d’un ensemble de scénarios possibles lors d’une session de simulation ainsi que par la distribution des actions réalisables entre les différents acteurs (réels ou virtuels) intervenant dans la simulation. Cette présentation reprend les travaux de thèse de Guillaume, réalisée dans le cadre du projet de rechercheS3PM du labex Cominlabs.
-Da Vinci robotic prostatectomy that is increasingly performed for minimally invasive prostatic tumor resection uses stereoscopic laparoscopes to intuitively visualize the organ surface in the body and manipulate various surgical tools under the insufficient light sources and the relatively narrow field of view of the binocular stereoscopic laparoscope that usually limits the visualization on the organ being operated on and its anatomical surroundings. Surgical vision augmentation in accordance with non-uniform illumination correction, fast visibility-contrast fusion defogging, motion magnification, and surgical filed 3D reconstruction techniques to maintain and augment a clear field of in-situ direct vision in robotic prostatectomy is paramount not only for safety by preventing inadvertent injury, but also to improve precision and reduce operative time.
+**September 20, 2016 : Integration of Medical Ontologies into the Framework of a Top-level Ontology** \\
+  * **Speaker:** Chantal Julliard\\
+  * **Sumarry:** Chantal did her studies in Mechanical Engineering at the Karlsruhe Institute of Technologies in Germany focusing on Biomedical Engineering. In her Master’s thesis she worked on medical ontologies and during her PhD she will work on Modelling Surgical Gestures for a Man-Machine Collaborative Training. Within her presentation she will share her master project and explain why and how to design a good ontology, particularly for laparoscopic surgeries.
+**September 13, 2016 : Deep learning: Covolutional Neural Networks** \\
+  * **Speaker:** Olga Dergachyova\\
+  * **Sumarry:** Le deep learning (apprentissage profond en français) est un ensemble de méthodes d'apprentissage automatiques tentant de modéliser avec un haut niveau d’abstraction des données grâce à un graph profond avec multiple couches de traitement composées de nombreuses transformations linéaires et non-linéaires. Ces tecniques ont démontré qu'elles étaient capables de produire d'excellents résultats pour différentes problématiques dans des champs d'application tels que la vision par ordinateur, la reconnaissance automatique de la parole et du langage naturel. Dans ma présentation je vais me concentrer sur le réseau neuronal convolutif (CNN), le type de réseau de neurones le plus utilisé actuellement. Je vais introduire le concept général, parler de la structure du réseau et de son apprentissage. Ensuite je présenterai les problèmatiques et les directions de recherche les plus vives dans ce domaine, ainsi que des exemples d'application.
-===== Mardi 27 septembre 2016 13:00-14:00 =====
+**July 05, 2016 : Intepersonal non technical skills in neurosurgery** \\
-==== "Séquencement d'actions en environnement virtuel collaboratif" ====
+  * **Speaker:** Pierre-Louis Hénaux\\
-Présenté par : Guillaume Claude
+  * **Sumarry:** The talk will consist of three parts: (1)Presentation of "PACTE project (evaluation of teamworking in emergency operative room)"; (2) Quantitative evaluation of non technical skills in neurosurgery; (3) Presentation of "Influence of team familiarity in Neurosurgical OR"
-Un environnement virtuel interactif à lui seul ne permet pas de répondre à tous les besoins liés à son utilisation. Dans le cadre de la formation par Réalité Virtuelle, un cadrage de l’activité de l’apprenant est important pour offrir une formation efficace. Le problème est le même dans les fictions interactives : seul, l’environnement n’offre qu’un intérêt limité. Nous nous intéressons ici au problème de la spécification du séquencement des actions dans un environnement  collaboratif. Il s’agit de définir puis de contrôler ce qui peut ou doit se passer au cours de la simulation dans un contexte potentiellement multiutilisateur. Ceci passe, entre autres, par la spécification (puis l’exécution) d’un ensemble de scénarios possibles lors d’une session de simulation ainsi que par la distribution des actions réalisables entre les différents acteurs (réels ou virtuels) intervenant dans la simulation.
+**May 24, 2016 : Représentation sémantique des biomarqueurs d'imagerie** \\
+  * **Speaker:** Emna Amdouni\\
+  * **Sumarry:** Le National Institute of Health a souligné le besoin de définir un vocabulaire lié au domaine des biomarqueurs d’imagerie afin de lever les ambiguïtés qui affectent ce concept. Plusieurs initiatives en ce sens ont émané de la part de diverses communautés (recherche en imagerie, radiologie, génétique, gestion des connaissances, etc.). Toutefois, jusqu’à aujourd’hui, aucun de ces travaux n’a réussi à répondre parfaitement à cette question. Notre travail vise à proposer une nouvelle façon d’aborder ce problème de représentation des biomarqueurs d’imagerie fondée sur les technologies du web sémantique 3.0 et consistant à définir explicitement les entités du domaine à couvrir grâce à des ontologies. Dans notre travail, nous proposons une ontologie générique intitulée «Imaging Biomarker Ontology» (IBO) qui définit les trois principaux aspects liés au concept de biomarqueur d’imagerie et qui sont: la qualité biologique mesurée, l’instrument de mesure et l’outil d’aide à la décision. Cette ontologie est une extension d’autres ontologies provenant de l’«Open Biological and Biomedical Ontologies Foundry». Elle a été, également, utilisée pour représenter des biomarqueurs d’imagerie (quantitatifs et qualitatifs) employés dans le domaine des gliomes cérébraux. Actuellement, nous travaillons sur la représentation sémantique des structures pathologiques et anatomiques qui sont présentes dans les IRMs cérébraux. Pour ce faire, nous avons choisi comme référence la terminologie VASARI qui fait intervenir des scores qui décrivent des qualités qualitatives et quantitatives.
-Cette présentation reprend les travaux de thèse de Guillaume, réalisée dans le cadre du projet de rechercheS3PM du labex Cominlabs.
+**May 10, 2016 : Reconnaissance de gestes pour une visualisation optimale d’injections naviguées** \\
+  * **Speaker:** Sébastien Muller\\
+  * **Sumarry:** Le but est l’identification de changements de phases chirurgicales lors d’interventions simples avec un nouvel ustensile (Multiguide) pour guider des injections et/ou biopsies. Les actions qui en découlent sont simplement de mettre à jour le système de navigation avec l’information la plus pertinente pour le chirurgien.Des atributs ont été définis basés sur des interventions simulées sur fantôme. Leur pouvoir de classification a été testé sur 25 séries réparties sur 5 opérateurs (3 chirugiens, 2 ingénieurs ayant connaissance de l’intervention). Nous avons testé la validité interne et externe des classifications. Des résultat préliminaires seront présentés.
-===== Mardi 20 septembre 2016 13:00-14:00 =====
+**April 25, 2016 : Pattern discovery for surgical skills analysis** \\
-==== "Integration of Medical Ontologies into the Framework of a Top-level Ontology" ====
+  * **Speaker:** Arnaud Huaulmé\\
-Présenté par : Chantal Julliard
-Chantal did her studies in Mechanical Engineering at the Karlsruhe Institute of Technologies in Germany focusing on Biomedical Engineering. In her Master’s thesis she worked on medical ontologies and during her PhD she will work on Modelling Surgical Gestures for a Man-Machine Collaborative Training. Within her presentation she will share her master project and explain why and how to design a good ontology, particularly for laparoscopic surgeries.
+**March 29, 2016 : Objective evaluation and feedback for training in deep brain stimulation planning** \\
+  * **Speaker:** Matthew Holden\\
+  * **Sumarry:** Develop of a virtual training course with an objective evaluation is of a high importance for improvement of planning skills of trainees in DBS. The software measures the performance of trainee based on two criteria : quality of trajectory and planning process, and provides an useful feedback to guide the trainee towards a good trajectory and acquire more experience in trajectory definition
+**March 15, 2016 : ADCAS: Automatic Detection in Computer-Assisted Surgery** \\
+  * **Speaker:** Olga Dergachyova\\
+  * **Sumarry:** ADCAS is a platform developed within the MediCIS team for detection of surgical workflow. The software is coded in C++ with use of Python scripts. Its pipeline includes 4 applications: data formatting, training, recognition and evaluation. The data formatting serves to process and transform the signals acquired in the OR in a appropriate and convenient format for the further use. It also creates two data sets: for training and for tests. The training application extracts features from input data in order to describe it and then learns a model of a chosen classifier to be able to distinguish surgical processes. The recognition application, the heart of the pipeline, predictes the workflow label of each test sample. The evaluation application allows to asses the performancies of the trained model and the choosen strategy. The whole platforme is highly modular based on a plugin system
+**February 23, 2016 : Advancing personalized treatments** \\
+  * **Speaker:** Valeria De Luca\\
+  * **Sumarry:** Valeria is Postdoc researcher in Computer Vision Laboratory and ETH Zurich (Switzerland) working on machine learning in neurointensive care. The presented us her two projects: one made during her PhD thesis and  one she is actually managing. The first project on liver ultrasound proposed generalized solutions for cancer treatments. The second project is for neurointensive care (ICU Cockpit) solution to specific clinical questions
-===== Mardi 13 septembre 2016 13:00-14:00 =====
+**February 09, 2016 : Reconnaissance de gestes pour une visualisation optimale d'injections naviguées** \\
-==== "Deep learning: Covolutional Neural Networks" ====
+  * **Speaker:** Sébastien Muller\\
-Présenté par : [[:members:olga.dergachyova:index| Olga Dergachyova]]
+  * **Sumarry:** Sébastien Muller vient du département de technologie médicale à la SINTEF et de l'institut de neuromédecine de l'université technologique NTNU à Trondheim, Norvège. Il est à Rennes afin de travailler sur de la modélisation de processus chirurgicaux dans le cadre d'une intervention appliquant un nouvel outil chirurgical pour guider des injections et biopsies. Le travail portera sur de la reconnaissance de gestes pour reconnaître les phases de l'intervention et mettre à jour le système de navigation avec l'information la plus pertinente pour le chirurgien. Durant son discours il nous a présenté le système de navigation CustusX et un outil développé à la SINTEF destiné à l’injection du toxine botulique dans un ganglion cervicale responsable de migraines fréquentes. Le défi est de reconnaître automatiquement les étapes principales de l’intervention afin de pouvoir mettre à jour la visualisation du navigateur selon les gestes du chirurgien
-Le deep learning (apprentissage profond en français) est un ensemble de méthodes d'apprentissage automatiques tentant de modéliser avec un haut niveau d’abstraction des données grâce à un graph profond avec multiple couches de traitement composées de nombreuses transformations linéaires et non-linéaires. Ces tecniques ont démontré qu'elles étaient capables de produire d'excellents résultats pour différentes problématiques dans des champs d'application tels que la vision par ordinateur, la reconnaissance automatique de la parole et du langage naturel.
+**February 02, 2016 : Introduction to formal language** \\
+  * **Speaker:** Yulong Zhao\\
+  * **Sumarry:** Formal language theory is concerned with the specification and manipulation of sets of strings of symbols, i.e., languages. Formal language theory is the heart of modern compiler architectures, regular expressions, parsers, web-scrappers, natural language processing (NLP), state machines based on markov chains, pattern matching.
-Dans ma présentation je vais me concentrer sur le réseau neuronal convolutif (CNN), le type de réseau de neurones le plus utilisé actuellement. Je vais introduire le concept général, parler de la structure du réseau et de son apprentissage. Ensuite je présenterai les problèmatiques et les directions de recherche les plus vives dans ce domaine, ainsi que des exemples d'application.
+**January 26, 2016 : Real-Time Workflow Analysis for Automatic Guidance in Image-Guided Needle Intervention Training** \\
+  * **Speaker:** Matthew Holden\\
+  * **Sumarry:** To augment expert supervision during medical intervention training, the use of computer-assisted training systems has been proposed. To be an asset in the training process, such systems should provide feedback to the trainee in the form of either skill evaluation or context-sensitive instruction. In this work, we address a key challenge in providing context-sensitive instruction during an intervention: identifying which task in the intervention's workflow the operator is performing. To this end, we have developed an intervention-independent algorithm which determines the ongoing task in real-time for interventions with arbitrary task ordering and repetition. The algorithm has been validated on two intervention datasets: freehand lumbar puncture and ultrasound-guided epidural. Relative to expert observer consistency, the proposed algorithm exhibits a mean accuracy of 93%. We suggest that this algorithm has sufficient task identification accuracy for use within a system which provides automated instruction to augment expert supervision in the training process. The proposed algorithm is implemented within the open-source Perk Tutor training platform (www.perktutor.org) for image-guided intervention training.
-===== Mardi 05 juillet 2016 13:00-14:00 =====
+===== Older =====
-==== "Intepersonal non technical skills in neurosurgery" ====
+**December 17, 2015 : Sequence Analysis for Surgical Process Modeling and Mining** \\
-Présenté par : [[:members:pierrelouis.henaux:index| Pierre-Louis Hénaux]]
+  * **Speaker:** Germain Forestier \\
+  * **Sumarry:** The goal of Surgical Process Modeling (SPM) is to support surgery through the quantitative analysis and understanding of operating room activities. This field is in constant growth with the increasing amount of data acquired in operating rooms. In this talk, I will give an overview of the work we carried out in the past few years on using sequence analysis to exact knowledge from recordings of surgical activities. I will highlight how we used and adapted Dynamic Time Warping (DTW) algorithm to automatically identify and understand complex surgical behaviors. I will also present our recent work focusing on the prediction of surgical activities and surgical phases. Finally, I will briefly discuss my other research interests including ontology engineering and pathology image analysis using deep learning
-The talk will consist of three parts:
+**December 03, 2015 : SurgeTrack, SurgePlan et SurgeLive : une suite logicielle basée SPM** \\
+  * **Speaker:** Guillaume Dardenne (b<>com, Rennes)\\
+  * **Sumarry:** La modélisation des procédures chirurgicales (Surgical Process Modelling, SPM) ouvre des perspectives extrêmement intéressantes tant sur la formation des chirurgiens, que sur l'assistance optimisée au bloc opératoire, ou bien encore la mesure d'indicateurs qualité pertinents associés à une procédure chirurgicale. Outre ces perspectives, l'utilisation de ces modèles en routine clinique ou pour la formation est encore timide.  Ceci peut s'expliquer par la non-standardisation de ces modèles et le manque d'outils adaptés qui répondent réellement aux exigences et aux contraintes du milieu chirurgical. Il existe par conséquent tout un travail de recherche à mener sur la standardisation de ces modèles mais également sur le développement d'outils innovants utilisables dans le contexte chirurgical et s'appuyant sur des modèles à priori de chirurgie. Nous allons ici vous présenter la suite logicielle SurgeSuite développée au sein de l'IRT b<>com en collaboration avec l'équipe MEDICIS. Cette suite est composée des logiciels : SurgeTrack pour l'enregistrement et l'analyse de modèles chirurgicaux ; SurgePlan pour la préparation d'une chirurgie ; et enfin, SurgeLive pour l'assistance au bloc opératoire. Nous réaliserons une démonstration des logicielles SurgeTrack et SurgePlan en cours de test sur plusieurs sites; et nous vous présenterons le concept associé au futur logiciel SurgeLive.
-  *     Presentation of "PACTE project (evaluation of teamworking in emergency operative room)"
+**November 26, 2015 : Knowledge support for multi-granularity and real-time modelling and recognition of surgical processes from multimodal sensors** \\
-  *     Quantitative evaluation of non technical skills in neurosurgery
+  * **Speaker:** Olga Dergachyova\\
-  *     Presentation of "Influence of team familiarity in Neurosurgical OR"
+  * **Sumarry:** The operating room is a high-risk and dynamic environment. Thus, improved integration of high technology, along with enhancement of teamwork, and coordination between services are essential to improve patient safety and comfort, augment efficiency and reduce the cost of care. A new paradigm called Operating Room of the Future has been introduced into the clinical environment. It aims to extend the perception and action of surgical staff. The realization of the this concept requires a context-aware system which understands actions and events having place in OR and descover the surgical workflow. In this presentation we describe knowledge-based method for surgical wokrflow detection and propose novel metrcis adapted for assesment of systems performing wokflow analysis.
+**November 10, 2015 : Qualitative assessment of Non Technical Skills in neurosurgical Operating Room: a focus on cognitive skills** \\
+  * **Speaker:** Pierre-Louis Henaux\\
+  * **Sumarry:** Non Technical Skills (NTS) in surgery can be assessed by external rating scales (NOTAS, NOTSS, NOTECHS). These scales seem to be well adapted to assess the interpersonal skills but incomplete to fully evaluate cognitive skills. Cognitive skills are indeed often non-verbalized and lack behavioral markers to decrypt them. Each surgeon has a different character and do not necessarily express orally all questions he may have during the intervention. Furthermore the emotional context and workload (mental readiness and workload distribution) of the surgeon may not be known by the team during the surgery. For example during an operation, the surgeon may have a family annoyance that will impact his mental readiness. It may be in a period of extreme fatigue or even himself having a disease (more or less severe) without be off work. Furthermore he may also have other professional events with deadlines to keep (teaching or research) forcing him to adapt his workload distribution and decreasing his mental readiness. Another example is interventions over a single day concatenation with a first intervention that goes wrong and a patient who has an adverse event (vital event or serious functional impairment) while the surgeon is performing a second surgery. All these factors can not be accurately described with simple generic scales. So it seems essential, for having a complete analysis of the NTS, to include a qualitative analysis of interviews with the surgeon after his intervention. A constructivist grounded theory study is an alternative to accurately analyze all these cognitive skills involved during the procedure.
-===== Mardi 24 mai 2016 13:00-14:00 =====
+**October 13, 2015 : Image-Guided Intervention Training Using the Open-Source Perk Tutor Platform** \\
-==== "Représentation sémantique des biomarqueurs d'imagerie" ====
+  * **Speaker:** Matthew Holden\\
-Présenté par : Emna Amdouni
+  * **Sumarry:** With the recent shift of medical education to a competency-based model, the use of objective measures of skill and automatic feedback systems has become increasingly important. This presentation will outline the Perk Tutor platform for image-guided intervention training (www.perktutor.org). The Perk Tutor is a free, open-source resource designed to facilitate medical education research and the development of image-guided intervention training curricula. The platform has been validated for both performance evaluation and automatic workflow analysis in a variety of applications, including spinal, central line, and prostate interventions
-Le National Institute of Health a souligné le besoin de définir un vocabulaire lié au domaine des biomarqueurs d’imagerie afin de lever les ambiguïtés qui affectent ce concept. Plusieurs initiatives en ce sens ont émané de la part de diverses communautés (recherche en imagerie, radiologie, génétique, gestion des connaissances, etc.). Toutefois, jusqu’à aujourd’hui, aucun de ces travaux n’a réussi à répondre parfaitement à cette question. Notre travail vise à proposer une nouvelle façon d’aborder ce problème de représentation des biomarqueurs d’imagerie fondée sur les technologies du web sémantique 3.0 et consistant à définir explicitement les entités du domaine à couvrir grâce à des ontologies.
+**September 29, 2015 : Detection of deviation in rectopexy surgery thanks to NLTS and HsMM** \\
-Dans notre travail, nous proposons une ontologie générique intitulée «Imaging Biomarker Ontology» (IBO) qui définit les trois principaux aspects liés au concept de biomarqueur d’imagerie et qui sont: la qualité biologique mesurée, l’instrument de mesure et l’outil d’aide à la décision. Cette ontologie est une extension d’autres ontologies provenant de l’«Open Biological and Biomedical Ontologies Foundry». Elle a été, également, utilisée pour représenter des biomarqueurs d’imagerie (quantitatifs et qualitatifs) employés dans le domaine des gliomes cérébraux. Actuellement, nous travaillons sur la représentation sémantique des structures pathologiques et anatomiques qui sont présentes dans les IRMs cérébraux. Pour ce faire, nous avons choisi comme référence la terminologie VASARI qui fait intervenir des scores qui décrivent des qualités qualitatives et quantitatives.
+  * **Speaker:** Arnaud Huaulmé\\
+  * **Sumarry:** Une opération chirurgicale ne se déroule pas toujours comme escompté. Celle-ci peut être perturbée par les spécificités du patient qui viennent modifier le planning, mais aussi par des événements indésirables pouvant avoir de lourdes conséquences. A partir des modèles individuels des procédures de rectopexie (iSPM), nous essayerons de détecter ces éléments en combinant l'utilisation d'une méthode d'alignement de séquence non-linéaire (NLTS) et des modèles semi-markovien cachés (HsMM
+**September 22, 2015 : Chemistry-inspired Adaptive Stream Processing** \\
+  * **Speaker:** Javier Rojas Balderrama\\
+  * **Sumarry:** {{:brainstorming:presentation_jrb_chemistry-inspired_adaptive_stream_processing.pdf|}}
-===== Mardi 10 mai 2016 13:00-14:00 =====
+**June 30, 2015 : Gate simulation toolkit: Overview** \\
-==== "Reconnaissance de gestes pour une visualisation optimale d’injections naviguées" ====
+  * **Speaker:** Frédéric Monge\\
-Présenté par : Sébastien Muller
+  * **Sumarry:** Geant4 is a toolkit for the simulation of the passage of particles through matter. Its areas of application include high energy, nuclear and accelerator physics, as well as studies in medical and space science.
+{{ :brainstorming:mobyctpet.png|}}
-Le but est l’identification de changements de phases chirurgicales lors d’interventions simples avec un nouvel ustensile (Multiguide) pour guider des injections et/ou biopsies. Les actions qui en découlent sont simplement de mettre à jour le système de navigation avec l’information la plus pertinente pour le chirurgien.Des atributs ont été définis basés sur des interventions simulées sur fantôme. Leur pouvoir de classification a été testé sur 25 séries réparties sur 5 opérateurs (3 chirugiens, 2 ingénieurs ayant connaissance de l’intervention). Nous avons testé la validité interne et externe des classifications. Des résultat préliminaires seront présentés.
-===== Mardi 25 avril 2016 13:00-14:00 =====
-==== "Pattern discovery for surgical skills analysis" ====
-Présenté par : [[:members:arnaud.huaulme:index| Arnaud Huaulmé]]
-===== Mardi 29 mars 2016 13:00-14:00 =====
-==== "Objective evaluation and feedback for training in deep brain stimulation planning" ====
-Présenté par : Matthew Holden
-Develop of a virtual training course with an objective evaluation is of a high importance for improvement of planning skills of trainees in DBS. The software measures the performance of trainee based on two criteria : quality of trajectory and planning process, and provides an useful feedback to guide the trainee towards a good trajectory and acquire more experience in trajectory definition.
-===== Mardi 15 mars 2016 13:00-14:00 =====
-==== "ADCAS: Automatic Detection in Computer-Assisted Surgery" ====
-Présenté par : [[:members:olga.dergachyova:index| Olga Dergachyova]]
-ADCAS is a platform developed within the MediCIS team for detection of surgical workflow. The software is coded in C++ with use of Python scripts. Its pipeline includes 4 applications: data formatting, training, recognition and evaluation. The data formatting serves to process and transform the signals acquired in the OR in a appropriate and convenient format for the further use. It also creates two data sets: for training and for tests. The training application extracts features from input data in order to describe it and then learns a model of a chosen classifier to be able to distinguish surgical processes. The recognition application, the heart of the pipeline, predictes the workflow label of each test sample. The evaluation application allows to asses the performancies of the trained model and the choosen strategy. The whole platforme is highly modular based on a plugin system.
-===== Mardi 23 février 2016 13:00-14:00 =====
-==== "Advancing personalized treatments" ====
-Présenté par : Valeria De Luca
-Valeria is Postdoc researcher in Computer Vision Laboratory and ETH Zurich (Switzerland) working on machine learning in neurointensive care. The presented us her two projects: one made during her PhD thesis and  one she is actually managing. The first project on liver ultrasound proposed generalized solutions for cancer treatments. The second project is for neurointensive care (ICU Cockpit) solution to specific clinical questions.
-===== Mardi 9 février 2016 13:00-14:00 =====
-==== "Reconnaissance de gestes pour une visualisation optimale d'injections naviguées" ====
-Présenté par : Sébastien Muller
-Sébastien Muller vient du département de technologie médicale à la SINTEF et de l'institut de neuromédecine de l'université technologique NTNU à Trondheim, Norvège. Il est à Rennes afin de travailler sur de la modélisation de processus chirurgicaux dans le cadre d'une intervention appliquant un nouvel outil chirurgical pour guider des injections et biopsies. Le travail portera sur de la reconnaissance de gestes pour reconnaître les phases de l'intervention et mettre à jour le système de navigation avec l'information la plus pertinente pour le chirurgien. Durant son discours il nous a présenté le système de navigation CustusX et un outil développé à la SINTEF destiné à l’injection du toxine botulique dans un ganglion cervicale responsable de migraines fréquentes. Le défi est de reconnaître automatiquement les étapes principales de l’intervention afin de pouvoir mettre à jour la visualisation du navigateur selon les gestes du chirurgien.
-===== Mardi 2 février 2016 13:00-14:00 =====
-==== "Introduction to formal language" ====
-Présenté par : [[:members:yulong.zhao:index| Yulong Zhao]]
-Formal language theory is concerned with the specification and manipulation of sets of strings of symbols, i.e., languages. Formal language theory is the heart of modern compiler architectures, regular expressions, parsers, web-scrappers, natural language processing (NLP), state machines based on markov chains, pattern matching.
-===== Mardi 26 janvier 2016 13:00-14:00 =====
-==== "Real-Time Workflow Analysis for Automatic Guidance in Image-Guided Needle Intervention Training" ====
-Présenté par : Matthew Holden
-To augment expert supervision during medical intervention training, the use of computer-assisted training systems has been proposed. To be an asset in the training process, such systems should provide feedback to the trainee in the form of either skill evaluation or context-sensitive instruction. In this work, we address a key challenge in providing context-sensitive instruction during an intervention: identifying which task in the intervention's workflow the operator is performing. To this end, we have developed an intervention-independent algorithm which determines the ongoing task in real-time for interventions with arbitrary task ordering and repetition. The algorithm has been validated on two intervention datasets: freehand lumbar puncture and ultrasound-guided epidural. Relative to expert observer consistency, the proposed algorithm exhibits a mean accuracy of 93%. We suggest that this algorithm has sufficient task identification accuracy for use within a system which provides automated instruction to augment expert supervision in the training process. The proposed algorithm is implemented within the open-source Perk Tutor training platform (www.perktutor.org) for image-guided intervention training.
-===== Jeudi 17 décembre 2015 13:00-14:00 =====
-==== "Sequence Analysis for Surgical Process Modeling and Mining" ====
-Présenté par : Germain Forestier
-The goal of Surgical Process Modeling (SPM) is to support surgery through the quantitative analysis and understanding of operating room activities. This field is in constant growth with the increasing amount of data acquired in operating rooms. In this talk, I will give an overview of the work we carried out in the past few years on using sequence analysis to exact knowledge from recordings of surgical activities. I will highlight how we used and adapted Dynamic Time Warping (DTW) algorithm to automatically identify and understand complex surgical behaviors. I will also present our recent work focusing on the prediction of surgical activities and surgical phases. Finally, I will briefly discuss my other research interests including ontology engineering and pathology image analysis using deep learning.
-===== Jeudi 3 décembre 2015 13:00-14:00 =====
-==== "SurgeTrack, SurgePlan et SurgeLive : une suite logicielle basée SPM" ====
-Présenté par : Guillaume Dardenne
-La modélisation des procédures chirurgicales (Surgical Process Modelling, SPM) ouvre des perspectives extrêmement intéressantes tant sur la formation des chirurgiens, que sur l'assistance optimisée au bloc opératoire, ou bien encore la mesure d'indicateurs qualité pertinents associés à une procédure chirurgicale.
-Outre ces perspectives, l'utilisation de ces modèles en routine clinique ou pour la formation est encore timide.  Ceci peut s'expliquer par la non-standardisation de ces modèles et le manque d'outils adaptés qui répondent réellement aux exigences et aux contraintes du milieu chirurgical. Il existe par conséquent tout un travail de recherche à mener sur la standardisation de ces modèles mais également sur le développement d'outils innovants utilisables dans le contexte chirurgical et s'appuyant sur des modèles à priori de chirurgie.
-Nous allons ici vous présenter la suite logicielle SurgeSuite développée au sein de l'IRT b<>com en collaboration avec l'équipe MEDICIS. Cette suite est composée des logiciels : SurgeTrack pour l'enregistrement et l'analyse de modèles chirurgicaux ; SurgePlan pour la préparation d'une chirurgie ; et enfin, SurgeLive pour l'assistance au bloc opératoire. Nous réaliserons une démonstration des logicielles SurgeTrack et SurgePlan en cours de test sur plusieurs sites ; et nous vous présenterons le concept associé au futur logiciel SurgeLive.
-===== Jeudi 26 novembre 2015 13:00-14:00 =====
-==== "Knowledge support for multi-granularity and real-time modelling and recognition of surgical processes from multimodal sensors" ====
-Présenté par : [[:members:olga.dergachyova:index| Olga Dergachyova]]
-The operating room is a high-risk and dynamic environment. Thus, improved integration of high technology, along with enhancement of teamwork, and coordination between services are essential to improve patient safety and comfort, augment efficiency and reduce the cost of care. A new paradigm called Operating Room of the Future has been introduced into the clinical environment. It aims to extend the perception and action of surgical staff. The realization of the this concept requires a context-aware system which understands actions and events having place in OR and descover the surgical workflow. In this presentation we describe knowledge-based method for surgical wokrflow detection and propose novel metrcis adapted for assesment of systems performing wokflow analysis.
-===== Mardi 10 novembre 2015 13:00-14:00 =====
-==== "Qualitative assessment of Non Technical Skills in neurosurgical Operating Room: a focus on cognitive skills." ====
-Présenté par : Pierre-Louis Henaux.
-Non Technical Skills (NTS) in surgery can be assessed by external rating scales (NOTAS, NOTSS, NOTECHS). These scales seem to be well adapted to assess the interpersonal skills but incomplete to fully evaluate cognitive skills. Cognitive skills are indeed often non-verbalized and lack behavioral markers to decrypt them. Each surgeon has a different character and do not necessarily express orally all questions he may have during the intervention. Furthermore the emotional context and workload (mental readiness and workload distribution) of the surgeon may not be known by the team during the surgery. For example during an operation, the surgeon may have a family annoyance that will impact his mental readiness. It may be in a period of extreme fatigue or even himself having a disease (more or less severe) without be off work. Furthermore he may also have other professional events with deadlines to keep (teaching or research) forcing him to adapt his workload distribution and decreasing his mental readiness. Another example is interventions over a single day concatenation with a first intervention that goes wrong and a patient who has an adverse event (vital event or serious functional impairment) while the surgeon is performing a second surgery. All these factors can not be accurately described with simple generic scales. So it seems essential, for having a complete analysis of the NTS, to include a qualitative analysis of interviews with the surgeon after his intervention. A constructivist grounded theory study is an alternative to accurately analyze all these cognitive skills involved during the procedure.
-===== Mardi 13 octobre 2015 13:00-14:00 =====
-==== "Image-Guided Intervention Training Using the Open-Source Perk Tutor Platform." ====
-Présenté par : Matthew Holden.
-With the recent shift of medical education to a competency-based model, the use of objective measures of skill and automatic feedback systems has become increasingly important. This presentation will outline the Perk Tutor platform for image-guided intervention training (www.perktutor.org). The Perk Tutor is a free, open-source resource designed to facilitate medical education research and the development of image-guided intervention training curricula. The platform has been validated for both performance evaluation and automatic workflow analysis in a variety of applications, including spinal, central line, and prostate interventions.
-===== Mardi 29 septembre 2015 13:00-14:00 =====
-==== "Detection of deviation in rectopexy surgery thanks to NLTS and HsMM." ====
-Présenté par : [[:members:arnaud.huaulme:index| Arnaud Huaulmé]].
-Une opération chirurgicale ne se déroule pas toujours comme escompté. Celle-ci peut être perturbée par les spécificités du patient qui viennent modifier le planning, mais aussi par des événements indésirables pouvant avoir de lourdes conséquences. A partir des modèles individuels des procédures de rectopexie (iSPM), nous essayerons de détecter ces éléments en combinant l'utilisation d'une méthode d'alignement de séquence non-linéaire (NLTS) et des modèles semi-markovien cachés (HsMM).
-===== Mardi 22 septembre 2015 13:00-14:00 =====
-==== "Chemistry-inspired Adaptive Stream Processing". ====
-Présenté par : Javier Rojas Balderrama.
-{{:brainstorming:presentation_jrb_chemistry-inspired_adaptive_stream_processing.pdf|}}
-===== Mardi 30 juin 2015 13:00-14:00 =====
-==== "Gate simulation toolkit: Overview". ====
-Présenté par : [[:members:frederic.monge:index| Frédéric Monge]].
-Geant4 is a toolkit for the simulation of the passage of particles through matter. Its areas of application include high energy, nuclear and accelerator physics, as well as studies in medical and space science.
 GATE is an advanced opensource software developed by the international OpenGATE collaboration, based on Geant4 and dedicated to numerical simulations in medical imaging and radiotherapy. It currently supports simulations of Emission Tomography (Positron Emission Tomography - PET and Single Photon Emission Computed Tomography - SPECT), Computed Tomography (CT) and Radiotherapy experiments. Using an easy-to-learn macro mechanism to configurate simple or highly sophisticated experimental settings, GATE now plays a key role in the design of new medical imaging devices, in the optimization of acquisition protocols and in the development and assessment of image reconstruction algorithms and correction techniques. It can also be used for dose calculation in radiotherapy experiments.
-{{:brainstorming:mobyctpet.png|}}
+**June 16, 2015 : Programmation GPU** \\
+  * **Speaker:** David Bouget\\
-===== Mardi 16 juin 2015 13:00-14:00 =====
+  * **Sumarry:** David nous a exposé l'intérêt du passage du CPU au GPU pour les calculs parallèles notamment en comparant leurs structures et capacités de calcules. La base et le modèle de programmation ont été également présentés. Les configuration d'exécution, navigation entre les threads, accès au mémoire et fonctions kernel ont été examinés.
-==== "Programmation GPU". ====
-Présenté par : [[:members:david.bouget:index| David Bouget]], Ph.D.
-David nous a exposé l'intérêt du passage du CPU au GPU pour les calculs parallèles notamment en comparant leurs structures et capacités de calcules. La base et le modèle de programmation ont été également présentés. Les configuration d'exécution, navigation entre les threads, accès au mémoire et fonctions kernel ont été examinés.
-===== Jeudi 20 mars 2014 13:00-14:00 =====
-==== "Objective skill assessment and training method for laparoscopic surgery". ====
-Présenté par : Munenori UEMURA Ph.D., As.P.E.Jp.
-Center for Advanced Medical Innovation Kyushu University - Kyushu University Hospital, Fukuoka, Japan.
-===== Mardi 18 mars 2014 13:00-14:00 =====
-==== "De l'indéxation d'évènements dans des films -- Application à la détection de violence". ====
-Présenté par : Cedric Penet, PhD.
-===== Mardi 28 janvier 2014 13:00-14:00 =====
-==== "Image Guided Surgery". ====
-Présenté par : Louis Collins, Prof. PhD.
-Montreal Neurological Institute - McGill University, Quebec, Canada.
-===== Mardi 21 janvier 2014 13:00-14:00 =====
-==== Des connaissances procédurales à la commande de robot chirurgicaux en chirurgie laparoscopique. ====
-Présenté par : Fabien Despinoy, Phd student
-LIRMM - Département Robotique,  équipe DEXTER.
-===== Mardi 14 janvier 2014 13:00-14:00 =====
-==== Acquisition, visualisation et reconstruction 3D de données anatomiques issues de dissection : application aux fibres blanches cérébrales. ====
-Présenté par : Barthélemy Serres, Phd - Post doc
-UMRS U930, Inserm/Université de Tours - "Imagerie et cerveau".
-===== Mardi 10 décembre 2013 13:00-14:00 =====
-==== Improving intracranial EEG by optimizing depth electrode trajectory planning ====
-Présenté par :  Rina Zelmann, PhD
-The McConnell Brain Imaging Center
-Montreal Neurological Institute, McGill University, Quebec, Canada.
-===== Mardi 5 novembre 2013 13:00-14:00 =====
-==== Activités sur le projet CREDIBLE (fédération de données d'imagerie). ====
-Présenté par : Bernard Gibaud.
-===== Mardi 22 octobre 2013 13:00-14:00 =====
-==== Démonstration de pyDBS: interface dédiée création d'atlas et parcours de bases de donnée" ====
-Présenté par : Gregory Laheurte.
-===== Mardi 8 octobre 2013 13:00-14:00 =====
-==== Real time surgical tool recognition: a journey in Saarbrücken. ====
-Présenté par : David Bouget.
-===== Mardi 1er octobre 2013 13:00-14:00 =====
-==== Présentation du laboratoire de l'université Kyūshū à Fukuoka, Japon & futures collaboration ====
-Présenté par : Pierre Jannin.
-===== Mardi 17 septembre 2013 13:00-14:00 =====
-==== Présentation du séjour de 3 mois à la Technische Universität München, Allemagne ====
-Présenté par : Frédéric Monge.
-===== Mardi 10 septembre 2013 13:00-14:00 =====
-==== Présentation oral de MASTER II SIBM (Signaux et Images en Biologie et Médecine) ====
-Présenté par : Pierre-Jean Le Reste.
-===== Mardi 21 mai 2013 13:00-14:00 =====
+**March 20, 2014 : Objective skill assessment and training method for laparoscopic surgery** \\
-==== Nelles approches de partage de données dans les PACS et le projet ISIMED (IRT B-COM)====
+  * **Speaker:** Munenori UEMURA Ph.D., As.P.E.Jp. Center for Advanced Medical Innovation Kyushu University - Kyushu University Hospital, Fukuoka, Japan.\\
-Présenté par : Bernard Gibaud.
-===== Mardi 7 mai 2013 13:00-14:00 =====
-==== Empreintes connectionnelles et annotations sémantiques ====
-Présenté par : Tristan Moreau.
-===== Mardi 23 avril 2013 13:00-14:00 =====
-====  ====
-Présenté par : David Bouget.
-===== Mardi 9 avril 2013 13:00-14:00 =====
-==== Les fractales en neurosciences. ====
-Présenté par : Pierre-Jean Le Reste.
-===== Mardi 26 mars 2013 13:00-14:00 =====
-====  ====
-Présenté par : Gregory Laheurte.
-===== Mardi 12 mars 2013 13:00-14:00 =====
+**March 18, 2014 : De l'indéxation d'évènements dans des films -- Application à la détection de violence** \\
-==== ANNULE ====
+  * **Speaker:** Cedric Penet, PhD.\\
-Présenté par : Bernard Gibaud.
-===== Mardi 26 février 2013 13:00-14:00 =====
-====  ====
-Présenté par : Florent Lalys.
-===== Mardi 05 février 2013 13:00-14:00 =====
+**January 28, 2014 : Image Guided Surgery** \\
-==== Modeling potential fields and tissue activation in DBS  ====
+  * **Speaker:** Louis Collins, Prof. PhD. From Montreal Neurological Institute - McGill University, Quebec, Canada.\\
-**Présenté par** : Tiziano D'Albis
+**January 21, 2014 : Des connaissances procédurales à la commande de robot chirurgicaux en chirurgie laparoscopique** \\
+  * **Speaker:** Fabien Despinoy\\
-**Abstract**: A first step towards a better understanding of clinical outcomes and side-effects of Deep Brain Stimulation (DBS) consists in the estimation of the volume of neural tissue affected by the stimulation. Since this estimation is currently experimentally difficult, computational models have been proposed to shade light on this topic. The problem can be subdivided in two steps: 1) modeling of the potential field generated by DBS electrodes within the patient brain and 2) modeling of the neural response to this field. In this talk I review the current approaches found in literature for solving these two problems, with particular enphasis on the modeling of the potential field.
+**January 14, 2014 : Acquisition, visualisation et reconstruction 3D de données anatomiques issues de dissection : application aux fibres blanches cérébrales** \\
+  * **Speaker:** Barthélemy Serres from UMRS U930, Inserm/Université de Tours - "Imagerie et cerveau"\\
-===== Mardi 22 janvier 2013 13:00-14:00 =====
+**December 10, 2013 : Improving intracranial EEG by optimizing depth electrode trajectory planning ** \\
-==== ANNULE  ====
+  * **Speaker:** Rina Zelmann from Montreal Neurological Institute, McGill University, Quebec, Canada.\\
-===== Mardi 08 janvier 2013 13:00-14:00 =====
+**November 05, 2013 : Activités sur le projet CREDIBLE (fédération de données d'imagerie)** \\
-==== Présentation des thèses sur l'étude de l'utilisabilité de systèmes de chirurgie guidée par l'image et sur la stimulation cérébrale profonde ====
+  * **Speaker:** Bernard Gibaud.\\
-Présenté par : Pierre Jannin.
-===== Mardi 11 décembre 2012 13:00-14:00 =====
+**October 22, 2013 : Démonstration de pyDBS: interface dédiée création d'atlas et parcours de bases de donnée** \\
-====  ====
+  * **Speaker:** Gregory Laheurte.\\
-**"Secrétariat MediCis - L'administratif et vous"**  \\
-Présenté par : Noémie Buisard
-===== Mardi 27 novembre 2012 13:00-14:00 =====
+**October 08, 2013 : Real time surgical tool recognition: a journey in Saarbrücken** \\
-==== Anatomical patient-specific model for Deep-Brain Stimulation ====
+  * **Speaker:** David Bouget\\
-**Présenté par** : Tiziano D'Albis
-**Abstract**: High frequency Deep Brain Stimulation (DBS) has been demonstrated as an effective minimally invasive surgical treatment for treating motor related diseases, e.g. Parkinson Disease, Essential Tremor, Tourette’s syndrome. The quality of clinical improvement, as well as the presence of side effects, strongly depend on the accuracy of electrode placement. Stimulation targets, however, are often difficult to localize from patient images and the choice of an optimal implantation trajectory is a time-demanding and tedious task. To support suregeons during DBS surgical planning we build patient-specific and generic models of anatomical and clinical data and automatically compute electrode trajectories from these models. In this talk I will give a general overview of our work on DBS surgical planning, focusing on the construction of an anatomical patient-specific model from multimodal images.
+**October 01, 2013 : Présentation du laboratoire de l'université Kyūshū à Fukuoka, Japon & futures collaboration ** \\
+  * **Speaker:** Pierre Jannin\\
-{{:presentation:pydbs_munich.pdf| Download }}
+**September 17, 2013 : Présentation du séjour de 3 mois à la Technische Universität München, Allemagne ** \\
+  * **Speaker:** Frédéric Monge\\
-===== Mardi 13 novembre 2012 13:00-14:00 =====
+**September 10, 2013 : Présentation oral de MASTER II SIBM (Signaux et Images en Biologie et Médecine) ** \\
-==== Sujet de thèse: Imagerie intra-opératoire naviguée pour l'optimisation de la chirurgie des tumeurs cérébrales. ====
+  * **Speaker:** Pierre-Jean Le Reste\\
-Présenté par : Frederic Monge.
-===== Mardi 30 octobre 2012 13:00-14:00 =====
+**May 21, 2013 : Nelles approches de partage de données dans les PACS et le projet ISIMED (IRT B-COM)** \\
-==== Quels outils en neuroimagerie ? ====
+  * **Speaker:** Bernard Gibaud\\
-Présenté par : Tristan Moreau.
-===== Mardi 16 octobre 2012 13:00-14:00 =====
-==== Etude exploratoire des interactions durant des opérations de Stimulation Cérébrale Profonde ====
-Présenté par : Martin Ragot.
+**May 07, 2013 : Empreintes connectionnelles et annotations sémantiques ** \\
+  * **Speaker:** Tristan Moreau\\
+**April 09, 2013 : Les fractales en neurosciences** \\
+  * **Speaker:** Pierre-Jean Le Reste\\
+**March 21, 2013 : Modèles numériques pour l'évaluation objective de la qualité d'images médicales** \\
+  * **Speaker:** Lu ZHANG-GE, Doctorante, LISA - Université d'Angers\\
+**March 18, 2013 : Advanced MRI Sequences ** \\
+  * **Speaker:** Giulio Gambarota, Professeur, LTSI - Rennes\\
+**March 11, 2013 : Organisations hautement fiables et prise de décision erronée :Retour d’expérience des bâtiments de surface de la Marine Nationale française ** \\
+  * **Speaker:** Sophie Le Bris et Dominique Martin. Centre de Recherche en Économie et Management, Unité Mixte de Recherche du CNRS qui associe des chercheurs du CNRS, de l’Université de Caen Basse-Normandie, et de l’Université de Rennes 1\\
+**February 14, 2013 : Approches cognitives symboliques et connaissances/formes a priori pour l’imagerie microscopique haut débit et haut contenu. Perspectives à travers des projets franco-singapouriens** \\
+  * **Speaker:** Daniel RACOCEANU. CNRS et Université Pierre et Marie Curie, Université Nationale de Singapour, Image & Pervasive Access Lab – IPAL, UMI CNRS, Singapour\\
-====== Collaboration and special events ======
+**February 05, 2013 : Modeling potential fields and tissue activation in DBS  ** \\
+  * **Speaker:** Tiziano D'Albis\\
+  * **Sumarry:** A first step towards a better understanding of clinical outcomes and side-effects of Deep Brain Stimulation (DBS) consists in the estimation of the volume of neural tissue affected by the stimulation. Since this estimation is currently experimentally difficult, computational models have been proposed to shade light on this topic. The problem can be subdivided in two steps: 1) modeling of the potential field generated by DBS electrodes within the patient brain and 2) modeling of the neural response to this field. In this talk I review the current approaches found in literature for solving these two problems, with particular enphasis on the modeling of the potential field.
-===== Thursday 21/03/2013 14:00-15:00: Modèles numériques pour l'évaluation objective de la qualité d'images médicales ====
+**January 08, 2013 : Présentation des thèses sur l'étude de l'utilisabilité de systèmes de chirurgie guidée par l'image et sur la stimulation cérébrale profonde ** \\
-Présenté par : Lu ZHANG-GE, Doctorante, LISA - Université d'Angers
+  * **Speaker:** Pierre Jannin\\
-===== Monday 18/03/2013 14:00-15:00: Advanced MRI Sequences ====
+**December 11, 2012 : Secrétariat MediCis - L'administratif et vous** \\
-Présenté par : Giulio Gambarota, Professeur, LTSI - Rennes
+  * **Speaker:** Noémie Buisard\\
-===== Monday 11/03/2013 12:00-13:00: Organisations hautement fiables et prise de décision erronée :Retour d’expérience des bâtiments de surface de la Marine Nationale française ====
+**November 27, 2012 : Anatomical patient-specific model for Deep-Brain Stimulation ** \\
-Présenté par : Sophie Le Bris et Dominique Martin. Centre de Recherche en Économie et Management, Unité Mixte de Recherche du CNRS qui associe des chercheurs du CNRS, de l’Université de Caen Basse-Normandie, et de l’Université de Rennes 1. http://www.ecole-navale.fr/Sophie-Le-Bris.html
+  * **Speaker:** Tiziano D'Albis\\
+  * **Sumarry:** High frequency Deep Brain Stimulation (DBS) has been demonstrated as an effective minimally invasive surgical treatment for treating motor related diseases, e.g. Parkinson Disease, Essential Tremor, Tourette’s syndrome. The quality of clinical improvement, as well as the presence of side effects, strongly depend on the accuracy of electrode placement. Stimulation targets, however, are often difficult to localize from patient images and the choice of an optimal implantation trajectory is a time-demanding and tedious task. To support suregeons during DBS surgical planning we build patient-specific and generic models of anatomical and clinical data and automatically compute electrode trajectories from these models. In this talk I will give a general overview of our work on DBS surgical planning, focusing on the construction of an anatomical patient-specific model from multimodal images. {{:presentation:pydbs_munich.pdf| Download }}
-===== Thursday 14/02/2013 14:00-15:00: Approches cognitives symboliques et connaissances/formes a priori pour l’imagerie microscopique haut débit et haut contenu. Perspectives à travers des projets franco-singapouriens. ====
+**November 13, 2012 : Sujet de thèse: Imagerie intra-opératoire naviguée pour l'optimisation de la chirurgie des tumeurs cérébrales** \\
-Présenté par : Daniel RACOCEANU. CNRS et Université Pierre et Marie Curie, Université Nationale de Singapour, Image & Pervasive Access Lab – IPAL, UMI CNRS, Singapour. http://ipal.i2r.a-star.edu.sg/
+  * **Speaker:** Frederic Monge\\
-==== Abstract ====
-L’intervention proposée est structurée en 3 parties :
-.	Présentation de l’Unité Mixte Internationale IPAL, basée à Singapour.
+**October 30, 2012 : Quels outils en neuroimagerie ? ** \\
-URL : http://ipal.i2r.a-star.edu.sg/
+  * **Speaker:** Tristan Moreau\\
-.	Exploration d’une lame virtuelle en utilisant une approche in vitro - in silico – in cognito. Application à la gradation du cancer du sein en histopathologie.
-Cadre : projet ANR TecSan MICO (Microscopie Cognitive) et plus récemment, le projet FUI FlexMIm
-URL : http://ipal.cnrs.fr/project/mico
-.	Approches probabilistes avec a priori de formes, analyse 2D – synthèse 3D pour le suivi et la différentiation des cellules souches neuronales. Reconstruction 3D de neurites / neurones.
-Cadre : Système de microscopie intégré pour le suivi des cellules souche neuronales et pour les structures complexes 3D – Projets A*STAR (Agency for Science Technology and Research)
-URL : http://ipal.cnrs.fr/project/ivs4nsc
-===== Thursday 05/07/2012 13:00-14:00 : "5D Image Analysis in Cardiac Image Analysis" =====
+**October 16, 2012 : Etude exploratoire des interactions durant des opérations de Stimulation Cérébrale Profonde ** \\
-Dr. Shuo Li, Image Research Scientist, Project Manager, GE Healthcare, Adjunct Research Professor,  Dept. of Medical Biophysics, Schulich School of Medicine and Dentistry, Adjunct Research Professor,  Dept. of Medical Imaging, Schulich School of Medicine and Dentistry, University of Western Ontario.
+  * **Speaker:** Martin Ragot\\
-==== Abstract ====
+**July 05, 2012 : 5D Image Analysis in Cardiac Image Analysis** \\
-Five-dimensional (5D) image processing has become a major challenge within the field of medical imaging.  5D images, i.e dynamic 3D images (4D) that are acquired at multiple times. A typical application in cardiac image analysis would include dynamic cardiac CT scans and/or gated cardiac MRI acquired at 3-monthly intervals and dynamic cell growth and shape change in weekly intervals. 4D images provide research a great assistance on analysis of the deformation and motion. The pattern of this deformation and motion can be used for recognition and diagnosis when another dimension is added. Another dimension usually comes from atlas, template, historical data and etc. After integrated with another dimensional data, the got the 5D we talk about.  The correlations in 5th dimension (e.g. the pattern of deformation for dynamic cardiac CT) can be extracted for recognition, tracking and diagnosis. During presentation, a group of experiments and validation will be presented to demonstrate the strength of 5D processing in cardiac image analysis.
+  * **Speaker:** Dr. Shuo Li, Image Research Scientist, Project Manager, GE Healthcare, Adjunct Research Professor,  Dept. of Medical Biophysics, Schulich School of Medicine and Dentistry, Adjunct Research Professor,  Dept. of Medical Imaging, Schulich School of Medicine and Dentistry, University of Western Ontario\\
+    * **Abstract:** Five-dimensional (5D) image processing has become a major challenge within the field of medical imaging.  5D images, i.e dynamic 3D images (4D) that are acquired at multiple times. A typical application in cardiac image analysis would include dynamic cardiac CT scans and/or gated cardiac MRI acquired at 3-monthly intervals and dynamic cell growth and shape change in weekly intervals. 4D images provide research a great assistance on analysis of the deformation and motion. The pattern of this deformation and motion can be used for recognition and diagnosis when another dimension is added. Another dimension usually comes from atlas, template, historical data and etc. After integrated with another dimensional data, the got the 5D we talk about.  The correlations in 5th dimension (e.g. the pattern of deformation for dynamic cardiac CT) can be extracted for recognition, tracking and diagnosis. During presentation, a group of experiments and validation will be presented to demonstrate the strength of 5D processing in cardiac image analysis.
-{{ :brainstorming:dsc08303c.jpg}}
+**June 22, 2012 : Medical Robotics at Waseda University: Takanishi-Lab (RT for Medical Education)** \\
-===== Friday 22/06/2012 13:00-14:00 : "Medical Robotics at Waseda University" =====
+  * **Speaker:** Dr. Hiroyuki ISHII, Takanishi-Lab, Waseda University\\
-Dr. Hiroyuki ISHII, Takanishi-Lab, Waseda University, Dr. Takeharu HOSHI, Fujie-Lab, Waseda University.
+  * **Sumarry:** {{ :brainstorming:dsc08303c.jpg}} Takanishi-Lab has been conducting research on robotic patient simulator for physicians training. We will present a new robotic simulator for suture/ligature procedures. This simulator with embedded sensors measures applied force during suturing/ligaturing and captures condition of the stitches to evaluate the performance scores for the suture/ligature process. We also will present a new humanoid for training of airway management. This humanoid mimics different kinds of patient’s motor functions in the TMJ (temporomandibular joint) and neck, where several sensors are implemented in the tongue and teeth of the humanoid to measure the applied force by trainee.
-===== Abstract =====
-   * Fujie-Lab (Medical and Assistive Robotics Laboratory)
-Fujie-Lab has been developing new medical robots which are controlled using biomechanical properties of human, such as material mechanics, dynamics, thermo dynamics and fluid dynamics. This means that we transform experimental knowledge of surgeons into biomechanical quantitative properties. We will highlight some of the work carried out by us and will present how these new approach may help to improve surgical treatments.
-  * Takanishi-Lab (RT for Medical Education)
-Takanishi-Lab has been conducting research on robotic patient simulator for physicians training. We will present a new robotic simulator for suture/ligature procedures. This simulator with embedded sensors measures applied force during suturing/ligaturing and captures condition of the stitches to evaluate the performance scores for the suture/ligature process. We also will present a new humanoid for training of airway management. This humanoid mimics different kinds of patient’s motor functions in the TMJ (temporomandibular joint) and neck, where several sensors are implemented in the tongue and teeth of the humanoid to measure the applied force by trainee.
+**June 22, 2012 : Medical Robotics at Waseda University: Fujie-Lab (Medical and Assistive Robotics Laboratory)** \\
+  * **Speaker:** Dr. Takeharu HOSHI, Fujie-Lab, Waseda University\\
+  * **Sumarry:** Fujie-Lab has been developing new medical robots which are controlled using biomechanical properties of human, such as material mechanics, dynamics, thermo dynamics and fluid dynamics. This means that we transform experimental knowledge of surgeons into biomechanical quantitative properties. We will highlight some of the work carried out by us and will present how these new approach may help to improve surgical treatments
-{{ :brainstorming:navab-brainstorming-mecis.png}}
+**May 02, 2012 : Computer Assisted Interventions: Challenges in design, development, validation and deployment of novel techniques** \\
+  * **Speaker:** Pr. Nassir Navab : chair for Computer Aided Medical Procedures & Augmented Reality Institut für Informatik I16, TU Munich, Germany.\\
+  * **Sumarry:** {{ :brainstorming:navab-brainstorming-mecis.png}}
-===== Wednesday 02/05/2012 13:00-14:00 : "Computer Assisted Interventions: Challenges in design, development, validation and deployment of novel techniques" =====
-Pr. Nassir Navab : chair for Computer Aided Medical Procedures & Augmented Reality Institut für Informatik I16, TU Munich, Germany.