You are here: indexactivitiestheme1projectsspm

Differences

This shows you the differences between the selected revision and the current version of the page.

activities:theme1:projects:spm:index 2010/12/08 13:52 activities:theme1:projects:spm:index 2016/01/05 14:34 current
Line 4: Line 4:
  * [[members:pierre.jannin:index|Pierre Jannin]] - Leader   * [[members:pierre.jannin:index|Pierre Jannin]] - Leader
-  * [[members:brivael.trelhu:index|Brivael Trelhu]] - PhD student +  * [[members:florent.lalys:index|Florent Lalys]] - PhD student (2009-2012) 
-  * [[members:xavier.morandi:index|Xavier Morandi]] - Medical expert +  * [[members:xavier.morandi:index|Xavier Morandi]] - Neurosurgeon - Medical expert 
-  * [[members:laurent.riffaud:index|Laurent Riffaud]] - Medical expert +  * [[members:laurent.riffaud:index|Laurent Riffaud]] - Neurosurgeon - Medical expert - PhD student (2009-2012) 
-  * [[members:jean-yves.gauvrit:index|Jean Yves Gauvrit]] - Medical expert+  * [[members:germain.forestier:index|Germain Forestier]] - Post doc (2012) 
 +  * Visiting guest researchers: M. Uemura (Kyushu University Japan, 3*2 weeks), D. Katic (Karlsruhe Institute of Technology, Germany, 3 months)
====== General purpose ====== ====== General purpose ======
-One of aspects of understanding the decision-making process in accomplishing a surgical procedure relies on its explicit description. Descriptions of the main surgical procedures (means of first excision techniques ...), complemented by a multitude of items of technical notes from notice of experts or clinical cases can be find in many surgical books and journals. All of them were performed by manual review of cases. So, it seems there are no specific works for the creation of such generic procedure models created from patient-specific models which describe surgical cases. To get them, it is necessary to have formal and explicit descriptions of the procedures carried out including both the information available before the operation (predictive data) but also the various techniques used supplemented by the use of instruments (taking into account their role and their impact on the surgical place). 
-====== Description ====== +The concept of surgical process models (SPM), we introduced about 15 years ago, is now emerging as a key element of the operating room of the future, assuming that an optimal surgical support system needs to be adapted to the different surgical times with an explicit understanding of the surgical process (named situation awareness). Surgical process models are descriptions of the surgical or interventional procedure formalized and represented into structured forms. Different granularity levels of the procedure may be studied from a high-level objective-based list of main surgical or interventional phases, to a list of the physical actions performed by the surgeons and recorded during surgery, to the spatial description of each physical gesture and tool. For example, a classical representation of the surgical actions performed during a surgical process consists in a sequential list of n-uplets describing each single surgical action by a verb, the operator performing the action, the surgical tool, the targeted anatomical, pathological and/or functional structure(s), the body part concerned by the performance of this action, the starting and ending times of the action, the needed information for performing this action, and some additional attributes characterizing the action.
-{{ :activities:theme1:projects:spm:image4.jpg?400 }} +
-**The Need**+
-In recent years, due to the progress of medicine and computers, there has been an increased use of technologies in healthcare systems, from the hospital administration to the Operating Room (OR). In particular, the OR has undergone significant transformations to evolve into a highly complex and technologically rich environment. Computer technologies are now increasingly used throughout the intervention, from pre-operative planning and surgical performance to post-operative assessment. Computer-assisted-surgery (CAS) or Computer-assisted Intervention (CAI) has therefore a vital role in current surgeries performance. For instance, during surgical planning, CAS provides access to multimodal images and information about the patient and the possible simulation of parts of the surgical procedure. During surgery, it provides visualisation of pre- and intra-operative information on the patient with regards to the operative field, and passive or active support of surgery by means of tool localisation or robotics. Additionally, all computer-driven tools provide real improvements to the ergonomics of the OR that increase medical safety, optimise operating time and support decision making that give a significant advantage over conventional techniques.  
 +====== Results ======
 +{{ :activities:theme1:projects:spm:image4.jpg?400 }}
-{{ :activities:theme1:projects:spm:test.jpg?400}}+We studied two granularity levels: surgical steps and actions. We first redesigned the ontology for describing this symbolic data. Then, we developed a software for observer based descriptions of individual surgical procedures from live observations or from video, resulting in individual SPMs. More than 100 procedures were described from live observations in Operating Rooms (OR). We then proposed original methods for analysing these descriptions based on sequence alignment approaches. We demonstrated the added value of such approaches for analysing surgical practice among surgeons and among international surgical departments. To the best of our knowledge, for the first time, we shown detailed quantitative and objective significant differences in surgical practice for spinal surgery and between 3 surgical centers in Canada, Germany and France. We also analysed the impact of different imaging techniques on processes for interventional neuroradiology. Observer based acquisition of individual descriptions of surgeries is a strong deadlock of this methodology. It is costly in term of human resources. To overcome such issue, we studied approaches for automatic recognition of surgical steps and actions from video images of cataract and pituitary surgery. The approach was based on computer vision and machine learning. We demonstrated the feasibility of such fully automatic approach with recognition rate of about 95% for steps and 70% for actions. This work was done in collaboration with Carl Zeiss and was awarded by the 2nd Best PhD thesis of University of Rennes 1.
-**Workflows**+==== Awards ====
-In most current medical procedures and applications, the sequence of surgical steps and actions that are accomplished to perform a treatment follows a repetitive schema. This schema is usually called a workflow. Workflows structure the performance of the operation, from the first incision on the patient to the last suturing. In regular operations, patient and surgeon specificities influence the surgical steps in their details. Workflows can be described in medical books, formalized by protocols and learnt by the personnel during medical studies and training.+  * 2nd Best PhD thesis University of Rennes 1,  
 +  * 2015 Best paper award at Artificial Intelligence in Medicine Europe conference (AIME) Avia, Italy June 2015
-**Methods**+{{ :activities:theme1:projects:spm:test.jpg?400}}
-We use **live recorded surgical procedures** and **preoperative informations** to create **surgical models**. Each record contains every activities of the surgery. Each activity was coded by the association of an action, an instrument, and an anatomical structure defining a triplet. +Main grants : Inserm, Région Bretagne, LabEx CAMI
-With these recorded surgeries, we can+==== Main Collaborators ====
-¤ use **statistical methods** to compare different populations : for example studying differences between juniors and seniors surgeons+  * Université of Haute Alsace (Mulhouse): Germain Forestier 
 +  * Karlsruhe Institute of Technology, Karlsruhe (Germany) 
 +  * [[http://www.bic.mcgill.ca|Pr. Louis Collins MNI McGill University Canada]] 
 +  * [[http://www.iccas.de|Thomas Neumuth ICCAS University of Leipzig Germany]] 
 +  * [[http://www.ifcars.org|Pr. Heinz Lemke IFCARS Germany]]
-¤ extract **rules** which can be represented by networks like the figure on the right (which represents one phase of a RCVA surgery)+====== Publications ======
-====== Main Collaborators ====== +<html> 
- +<span id="halpublispm">
-  * [[http://www.iccas.de|Thomas Neumuth ICCAS University of Leipzig Germany]] +
-  * [[http://www.ifcars.org|Pr. Heinz Lemke IFCARS Germany]] +
-  * [[members:brivael.trelhu:index|J.Y. Gauvrit Service de Neuroradiologie CHU Rennes]]+
 +<p><iframe width="99%" scrolling="no" height="2000" frameborder="0" src="
 +https://haltools.archives-ouvertes.fr/Public/afficheRequetePubli.php?annee_publideb=1996&collection_exp=LTSI%3BUNIV-RENNES1&solrQuery=%28authFullName_t%3A%22jannin%22+AND+authFullName_t%3A%22forestier%22%29+OR+%28authFullName_t%3A%22jannin%22+AND+authFullName_t%3A%22riffaud%22%29&CB_auteur=oui&CB_titre=oui&CB_article=oui&langue=Anglais&tri_exp=annee_publi&tri_exp2=typdoc&tri_exp3=date_publi& amp;ord re_aff=TA&Fen=Aff&css=https://halur1.univ-rennes1.fr/css/publis-HAL.css></iframe></p>
 +</span>
 +</html>
inserm rennes1 ltsi