Computer Vision Analysis of Intraoperative Video
- 1 September 2019
- journal article
- conference paper
- Published by Ovid Technologies (Wolters Kluwer Health) in Annals of Surgery
- Vol. 270 (3), 414-421
- https://doi.org/10.1097/sla.0000000000003460
Abstract
To develop and assess AI algorithms to identify operative steps in laparoscopic sleeve gastrectomy (LSG). Computer vision, a form of artificial intelligence (AI), allows for quantitative analysis of video by computers for identification of objects and patterns, such as in autonomous driving. Intraoperative video from LSG from an academic institution was annotated by 2 fellowship-trained, board-certified bariatric surgeons. Videos were segmented into the following steps: 1) port placement, 2) liver retraction, 3) liver biopsy, 4) gastrocolic ligament dissection, 5) stapling of the stomach, 6) bagging specimen, and 7) final inspection of staple line. Deep neural networks were used to analyze videos. Accuracy of operative step identification by the AI was determined by comparing to surgeon annotations. Eighty-eight cases of LSG were analyzed. A random 70% sample of these clips was used to train the AI and 30% to test the AI's performance. Mean concordance correlation coefficient for human annotators was 0.862, suggesting excellent agreement. Mean (±SD) accuracy of the AI in identifying operative steps in the test set was 82% ± 4% with a maximum of 85.6%. AI can extract quantitative surgical data from video with 85.6% accuracy. This suggests operative video could be used as a quantitative data source for research in intraoperative clinical decision support, risk prediction, or outcomes studies.Keywords
This publication has 21 references indexed in Scilit:
- Complementing Operating Room Teaching With Video-Based CoachingJAMA Surgery, 2017
- Video Coaching as an Efficient Teaching Method for Surgical Residents—A Randomized Controlled TrialJournal of Surgical Education, 2017
- Online time and resource management based on surgical workflow time series analysisInternational Journal of Computer Assisted Radiology and Surgery, 2016
- EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic VideosIEEE Transactions on Medical Imaging, 2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Multi-perspective workflow modeling for online surgical situation modelsJournal of Biomedical Informatics, 2015
- Real-Time Task Recognition in Cataract Surgery Videos Using Adaptive Spatiotemporal PolynomialsIEEE Transactions on Medical Imaging, 2014
- Use of Cognitive Task Analysis to Guide the Development of Performance-Based Assessments for IntraOperative Decision MakingMilitary Medicine, 2013
- Intra-operative decision making: More than meets the eyeJournal of Biomedical Informatics, 2011
- Long Short-Term MemoryNeural Computation, 1997