Retrieval of surgical phase transitions using reinforcement learning
This addresses the problem of noisy phase transitions in minimally invasive surgery video analysis for medical professionals, but it is incremental as it builds on existing segmentation methods.
The paper tackles surgical workflow segmentation by introducing a reinforcement learning model to identify phase transition timestamps instead of classifying every video frame, achieving results slightly under state-of-the-art with reduced frame processing (<60% and <20% in applications) and outperforming state-of-the-art at comparable cost when processing all frames.
In minimally invasive surgery, surgical workflow segmentation from video analysis is a well studied topic. The conventional approach defines it as a multi-class classification problem, where individual video frames are attributed a surgical phase label. We introduce a novel reinforcement learning formulation for offline phase transition retrieval. Instead of attempting to classify every video frame, we identify the timestamp of each phase transition. By construction, our model does not produce spurious and noisy phase transitions, but contiguous phase blocks. We investigate two different configurations of this model. The first does not require processing all frames in a video (only <60% and <20% of frames in 2 different applications), while producing results slightly under the state-of-the-art accuracy. The second configuration processes all video frames, and outperforms the state-of-the art at a comparable computational cost. We compare our method against the recent top-performing frame-based approaches TeCNO and Trans-SVNet on the public dataset Cholec80 and also on an in-house dataset of laparoscopic sacrocolpopexy. We perform both a frame-based (accuracy, precision, recall and F1-score) and an event-based (event ratio) evaluation of our algorithms.