Robust Surgical Phase Recognition From Annotation Efficient Supervision

TL;DR

This paper introduces a robust surgical phase recognition method that effectively handles missing annotations and reduces labeling effort through the SkipTag@K approach, achieving high accuracy with minimal supervision.

Contribution

It proposes a novel robust recognition technique for handling missing annotations and introduces the SkipTag@K annotation scheme to balance annotation effort and performance.

Findings

Achieves 85.1% accuracy on MultiBypass140 with only 3 frames per video

Demonstrates robustness to missing phase annotations in surgical data

Reduces annotation costs while maintaining competitive performance

Abstract

Surgical phase recognition is a key task in computer-assisted surgery, aiming to automatically identify and categorize the different phases within a surgical procedure. Despite substantial advancements, most current approaches rely on fully supervised training, requiring expensive and time-consuming frame-level annotations. Timestamp supervision has recently emerged as a promising alternative, significantly reducing annotation costs while maintaining competitive performance. However, models trained on timestamp annotations can be negatively impacted by missing phase annotations, leading to a potential drawback in real-world scenarios. In this work, we address this issue by proposing a robust method for surgical phase recognition that can handle missing phase annotations effectively. Furthermore, we introduce the SkipTag@K annotation approach to the surgical domain, enabling a flexible balance between annotation effort and model performance. Our method achieves competitive results on two challenging datasets, demonstrating its efficacy in handling missing phase annotations and its potential for reducing annotation costs. Specifically, we achieve an accuracy of 85.1\% on the MultiBypass140 dataset using only 3 annotated frames per video, showcasing the effectiveness of our method and the potential of the SkipTag@K setup. We perform extensive experiments to validate the robustness of our method and provide valuable insights to guide future research in surgical phase recognition. Our work contributes to the advancement of surgical workflow recognition and paves the way for more efficient and reliable surgical phase recognition systems.