Zero-shot 3D Segmentation of Abdominal Organs in CT Scans Using Segment Anything Model 2: Adapting Video Tracking Capabilities for 3D Medical Imaging

TL;DR

This study evaluates the zero-shot 3D segmentation performance of Segment Anything Model 2 on abdominal organs in CT scans, highlighting its strengths on larger organs and the impact of prompt settings on accuracy.

Contribution

It demonstrates SAM 2's capability for zero-shot segmentation of abdominal organs in CT scans and analyzes how prompt configurations affect results.

Findings

Larger organs achieved high DSC scores, e.g., liver 0.821, kidneys 0.862-0.870.

Smaller organs like pancreas and adrenal glands had lower DSCs.

Negative prompts and initial slice choice significantly affected segmentation accuracy.

Abstract

Objectives: To evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, and to investigate the effects of prompt settings on segmentation results. Materials and Methods: In this retrospective study, we used a subset of the TotalSegmentator CT dataset from eight institutions to assess SAM 2's ability to segment eight abdominal organs. Segmentation was initiated from three different z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the Dice similarity coefficient (DSC). We also analyzed the impact of "negative prompts," which explicitly exclude certain regions from the segmentation process, on accuracy. Results: 123 patients (mean age, 60.7 \pm 15.5 years; 63 men, 60 women) were evaluated. As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean DSCs as follows: liver 0.821 \pm 0.192, right kidney 0.862 \pm 0.212, left kidney 0.870 \pm 0.154, and spleen 0.891 \pm 0.131. Smaller organs showed lower performance: gallbladder 0.531 \pm 0.291, pancreas 0.361 \pm 0.197, and adrenal glands, right 0.203 \pm 0.222, left 0.308 \pm 0.234. The initial slice for segmentation and the use of negative prompts significantly influenced the results. By removing negative prompts from the input, the DSCs significantly decreased for six organs. Conclusion: SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs. Performance was significantly influenced by input negative prompts and initial slice selection, highlighting the importance of optimizing these factors.