Zero-shot Segmentation of Abdominal Adipose Tissue Using the Segment Anything Model

The findings revealed limitations in the zero-shot segmentation capabilities of SAM and MedSAM for specialized medical imaging tasks, particularly for adipose tissue quantification in abdominal CT. Although foundation models offer theoretical advantages in generalizability and deployment efficiency, their performance in specialized medical applications requires significant enhancement through task-specific fine-tuning, and optimized prompt engineering strategies. Further studies are required to enhance the clinical utility of these models for reliable and accessible fat segmentation.