You are here: indexnewsipcai2016award

Differences

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

news:ipcai2016award 2016/06/30 15:09 news:ipcai2016award 2016/06/30 15:10 current
Line 4: Line 4:
{{:news:image-30-06-16-14-48.png|}} {{:news:image-30-06-16-14-48.png|}}
-The paper was also selected as one of the 16 finalists for the Robert Wagner Best Student Paper of the whole SPIE Medical Imaging conference **(16 from 956 papers)**.  
- 
---- ----
**Automatic data-driven real-time segmentation and recognition of surgical workflow** \\  //O. Dergachyova, D. Bouget, A. Huaulmé, X. Morandi, P. Jannin// **Automatic data-driven real-time segmentation and recognition of surgical workflow** \\  //O. Dergachyova, D. Bouget, A. Huaulmé, X. Morandi, P. Jannin//
-**ABSTRACT** +**ABSTRACT** \\ 
-Purpose - With the intention of extending the perception and action of surgical staff inside the operating room, the medical community has expressed a growing interest towards context-aware systems. Requiring an accurate identification of the surgical workflow, such systems make use of data from a diverse set of available sensors. In this paper, we propose a fully data-driven and real-time method for segmentation and recognition of surgical phases using a combination of video data and instrument usage signals, exploiting no prior knowledge. We also introduce new validation metrics for assessment of workflow detection. +Purpose - With the intention of extending the perception and action of surgical staff inside the operating room, the medical community has expressed a growing interest towards context-aware systems. Requiring an accurate identification of the surgical workflow, such systems make use of data from a diverse set of available sensors. In this paper, we propose a fully data-driven and real-time method for segmentation and recognition of surgical phases using a combination of video data and instrument usage signals, exploiting no prior knowledge. We also introduce new validation metrics for assessment of workflow detection. \\ 
-Methods - The segmentation and recognition are based on a four-stage process. Firstly, during the learning time, a Surgical Process Model is automatically constructed from data annotations to guide the following process. Secondly, data samples are described using a combination of low-level visual cues and instrument information. Then, in the third stage, these descriptions are employed to train a set of AdaBoost classifiers capable of distinguishing one surgical phase from others. Finally, AdaBoost responses are used as input to a Hidden semi-Markov Model in order to obtain a final decision. +Methods - The segmentation and recognition are based on a four-stage process. Firstly, during the learning time, a Surgical Process Model is automatically constructed from data annotations to guide the following process. Secondly, data samples are described using a combination of low-level visual cues and instrument information. Then, in the third stage, these descriptions are employed to train a set of AdaBoost classifiers capable of distinguishing one surgical phase from others. Finally, AdaBoost responses are used as input to a Hidden semi-Markov Model in order to obtain a final decision. \\ 
-Results - On the MICCAI EndoVis challenge laparoscopic dataset we achieved a precision and a recall of 91 % in classification of 7 phases.+Results - On the MICCAI EndoVis challenge laparoscopic dataset we achieved a precision and a recall of 91 % in classification of 7 phases. \\
Conclusion - Compared to the analysis based on one data type only, a combination of visual features and instrument signals allows better segmentation, reduction of the detection delay and discovery of the correct phase order. Conclusion - Compared to the analysis based on one data type only, a combination of visual features and instrument signals allows better segmentation, reduction of the detection delay and discovery of the correct phase order.
inserm rennes1 ltsi