Thoracic Surgery Video Analysis for Surgical Phase Recognition
This work addresses automated workflow analysis for surgeons and medical trainees, but it is incremental as it applies existing models to a specific surgical domain.
This paper tackled surgical phase recognition in thoracic surgery videos by comparing frame-based and video-based methods, finding that a video-based approach using Masked Video Distillation achieved a top-1 accuracy of 72.9%, outperforming an image-based method at 52.31%.
This paper presents an approach for surgical phase recognition using video data, aiming to provide a comprehensive understanding of surgical procedures for automated workflow analysis. The advent of robotic surgery, digitized operating rooms, and the generation of vast amounts of data have opened doors for the application of machine learning and computer vision in the analysis of surgical videos. Among these advancements, Surgical Phase Recognition(SPR) stands out as an emerging technology that has the potential to recognize and assess the ongoing surgical scenario, summarize the surgery, evaluate surgical skills, offer surgical decision support, and facilitate medical training. In this paper, we analyse and evaluate both frame-based and video clipping-based phase recognition on thoracic surgery dataset consisting of 11 classes of phases. Specifically, we utilize ImageNet ViT for image-based classification and VideoMAE as the baseline model for video-based classification. We show that Masked Video Distillation(MVD) exhibits superior performance, achieving a top-1 accuracy of 72.9%, compared to 52.31% achieved by ImageNet ViT. These findings underscore the efficacy of video-based classifiers over their image-based counterparts in surgical phase recognition tasks.