When SAM Meets Medical Images: An Investigation of Segment Anything Model (SAM) on Multi-phase Liver Tumor Segmentation

TL;DR

This paper investigates the performance of the Segment Anything Model (SAM) on multi-phase liver tumor segmentation, revealing its limitations and potential as an interactive annotation tool in medical imaging.

Contribution

It is the first comprehensive study assessing SAM's capabilities in medical image segmentation, especially for liver tumors, highlighting its strengths and weaknesses.

Findings

SAM shows limited segmentation accuracy for MPLiTS.

Qualitative results indicate SAM's potential as an annotation tool.

Significant gap between SAM's performance and clinical requirements.

Abstract

Learning to segmentation without large-scale samples is an inherent capability of human. Recently, Segment Anything Model (SAM) performs the significant zero-shot image segmentation, attracting considerable attention from the computer vision community. Here, we investigate the capability of SAM for medical image analysis, especially for multi-phase liver tumor segmentation (MPLiTS), in terms of prompts, data resolution, phases. Experimental results demonstrate that there might be a large gap between SAM and expected performance. Fortunately, the qualitative results show that SAM is a powerful annotation tool for the community of interactive medical image segmentation.