Systematic Evaluation and Guidelines for Segment Anything Model in Surgical Video Analysis

TL;DR

This paper systematically evaluates the zero-shot performance of the SAM2 model in diverse surgical video datasets, revealing its strengths and limitations in complex surgical environments and guiding future adaptive solutions.

Contribution

It provides the first comprehensive assessment of SAM2's zero-shot capabilities in surgical videos across multiple procedures and challenges, offering valuable insights for future research.

Findings

SAM2 performs well in structured scenarios like instrument and multi-organ segmentation

Performance varies with surgical complexity and dynamic conditions

Highlights need for domain-specific adaptation and temporal coherence improvements

Abstract

Surgical video segmentation is critical for AI to interpret spatial-temporal dynamics in surgery, yet model performance is constrained by limited annotated data. The SAM2 model, pretrained on natural videos, offers potential for zero-shot surgical segmentation, but its applicability in complex surgical environments, with challenges like tissue deformation and instrument variability, remains unexplored. We present the first comprehensive evaluation of the zero-shot capability of SAM2 in 9 surgical datasets (17 surgery types), covering laparoscopic, endoscopic, and robotic procedures. We analyze various prompting (points, boxes, mask) and {finetuning (dense, sparse) strategies}, robustness to surgical challenges, and generalization across procedures and anatomies. Key findings reveal that while SAM2 demonstrates notable zero-shot adaptability in structured scenarios (e.g., instrument segmentation, {multi-organ segmentation}, and scene segmentation), its performance varies under dynamic surgical conditions, highlighting gaps in handling temporal coherence and domain-specific artifacts. These results highlight future pathways to adaptive data-efficient solutions for the surgical data science field.