ReSW-VL: Representation Learning for Surgical Workflow Analysis Using Vision-Language Model

TL;DR

This paper introduces ReSW-VL, a novel approach using a vision-language model with prompt learning to improve surgical workflow analysis and phase recognition accuracy.

Contribution

It proposes fine-tuning a CLIP-based vision-language model with prompt learning specifically for surgical phase recognition tasks.

Findings

Outperforms conventional methods on three datasets

Effective use of prompt learning for surgical phase recognition

Demonstrates the potential of vision-language models in surgical workflow analysis

Abstract

Surgical phase recognition from video is a technology that automatically classifies the progress of a surgical procedure and has a wide range of potential applications, including real-time surgical support, optimization of medical resources, training and skill assessment, and safety improvement. Recent advances in surgical phase recognition technology have focused primarily on Transform-based methods, although methods that extract spatial features from individual frames using a CNN and video features from the resulting time series of spatial features using time series modeling have shown high performance. However, there remains a paucity of research on training methods for CNNs employed for feature extraction or representation learning in surgical phase recognition. In this study, we propose a method for representation learning in surgical workflow analysis using a vision-language model (ReSW-VL). Our proposed method involves fine-tuning the image encoder of a CLIP (Convolutional Language Image Model) vision-language model using prompt learning for surgical phase recognition. The experimental results on three surgical phase recognition datasets demonstrate the effectiveness of the proposed method in comparison to conventional methods.