Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance

TL;DR

This paper introduces C2E, a self-supervised learning framework that uses compression and entropy maximization to learn effective representations from unlabeled surgical videos, enhancing various surgical AI tasks.

Contribution

C2E is a novel self-supervised approach leveraging Kolmogorov complexity and entropy maximization to improve surgical video understanding without labeled data.

Findings

C2E outperforms existing methods on multiple surgical tasks.

The model's representations better disentangle structural features.

C2E demonstrates strong generalization across diverse surgical datasets.

Abstract

Real-time video understanding is critical to guide procedures in minimally invasive surgery (MIS). However, supervised learning approaches require large, annotated datasets that are scarce due to annotation efforts that are prohibitive, e.g., in medical fields. Although self-supervision methods can address such limitations, current self-supervised methods often fail to capture structural and physical information in a form that generalizes across tasks. We propose Compress-to-Explore (C2E), a novel self-supervised framework that leverages Kolmogorov complexity to learn compact, informative representations from surgical videos. C2E uses entropy-maximizing decoders to compress images while preserving clinically relevant details, improving encoder performance without labeled data. Trained on large-scale unlabeled surgical datasets, C2E demonstrates strong generalization across a variety of surgical ML tasks, such as workflow classification, tool-tissue interaction classification, segmentation, and diagnosis tasks, providing improved performance as a surgical visual foundation model. As we further show in the paper, the model's internal compact representation better disentangles features from different structural parts of images. The resulting performance improvements highlight the yet untapped potential of self-supervised learning to enhance surgical AI and improve outcomes in MIS.