SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Model
This work assesses a foundation model for medical image segmentation, which could aid clinicians, but it is incremental as it applies an existing method to new data without major innovations.
The paper evaluated the Segment Anything Model (SAM) for zero-shot medical image segmentation on abdominal CT data, finding it generalizes well but does not reach state-of-the-art performance, with potential as a starting point for clinical tools.
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