Adaptation of Surgical Activity Recognition Models Across Operating Rooms

TL;DR

This paper presents a domain adaptation method for surgical activity recognition models to improve their generalizability across different operating rooms, using unlabeled and limited labeled videos to enhance performance.

Contribution

The work introduces a novel semi-supervised domain adaptation approach that generates pseudo labels for unlabeled surgical videos, improving model transferability across operating rooms.

Findings

Our method outperforms baselines on a dataset of 480+ surgical videos.

The approach effectively utilizes unlabeled videos for model adaptation.

Semi-supervised setting further enhances recognition accuracy.

Abstract

Automatic surgical activity recognition enables more intelligent surgical devices and a more efficient workflow. Integration of such technology in new operating rooms has the potential to improve care delivery to patients and decrease costs. Recent works have achieved a promising performance on surgical activity recognition; however, the lack of generalizability of these models is one of the critical barriers to the wide-scale adoption of this technology. In this work, we study the generalizability of surgical activity recognition models across operating rooms. We propose a new domain adaptation method to improve the performance of the surgical activity recognition model in a new operating room for which we only have unlabeled videos. Our approach generates pseudo labels for unlabeled video clips that it is confident about and trains the model on the augmented version of the clips. We extend our method to a semi-supervised domain adaptation setting where a small portion of the target domain is also labeled. In our experiments, our proposed method consistently outperforms the baselines on a dataset of more than 480 long surgical videos collected from two operating rooms.