A Multi Instance Learning Approach for Critical View of Safety Detection in Laparoscopic Cholecystectomy
Proceedings of the 7th Machine Learning for Healthcare Conference, PMLR 182:409-424, 2022.
Surgical procedures have a clear designated goal, which makes the art of performing surgery a task-oriented action. The performing surgeon follows specific workflow steps that describe the actions needed to reach the surgery goal. In ectomy procedures, such as Cholecystectomy and Appendectomy, the goal is to dissect and remove a specific organ. Safety measures are set to prevent injuries, and the surgeon needs to follow protective methods to avoid misidentification. In Laparoscopic Cholecystectomy (LC), this method is known as Critical View of Safety (CVS). This work illustrates that machine learning can detect CVS accurately enough to be used routinely in the clinical setting, both for educational purposes and in other assessment scenarios. We formulate CVS detection as a supervised Multi Instance Learning (MIL) problem and propose an attention-based MIL model that is trained and evaluated on more than 2,000 surgical videos. It achieves 82.6% mean unweighted accuracy in detecting LC CVS criteria and 84.2% accuracy in the final task of CVS detection.