SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Model

TL;DR

This paper evaluates the zero-shot medical image segmentation capabilities of the Segment Anything Model (SAM) on abdominal CT data, highlighting its potential as a starting point for medical segmentation tools despite not surpassing state-of-the-art performance.

Contribution

It provides an initial assessment of SAM's zero-shot performance on medical images, demonstrating its generalization ability and potential for further adaptation in medical segmentation.

Findings

SAM generalizes well to CT data

Potential for semi-automatic clinical segmentation tools

Not yet achieving state-of-the-art accuracy

Abstract

Foundation models have taken over natural language processing and image generation domains due to the flexibility of prompting. With the recent introduction of the Segment Anything Model (SAM), this prompt-driven paradigm has entered image segmentation with a hitherto unexplored abundance of capabilities. The purpose of this paper is to conduct an initial evaluation of the out-of-the-box zero-shot capabilities of SAM for medical image segmentation, by evaluating its performance on an abdominal CT organ segmentation task, via point or bounding box based prompting. We show that SAM generalizes well to CT data, making it a potential catalyst for the advancement of semi-automatic segmentation tools for clinicians. We believe that this foundation model, while not reaching state-of-the-art segmentation performance in our investigations, can serve as a highly potent starting point for further adaptations of such models to the intricacies of the medical domain. Keywords: medical image segmentation, SAM, foundation models, zero-shot learning