Segment anything model for medical image segmentation: Current applications and future directions

• Published in: Computers in biology and medicine Vol. 171; p. 108238
• Main Authors: Zhang, Yichi, Shen, Zhenrong, Jiao, Rushi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2024; Elsevier Limited
• Subjects: Benchmarking; Biology; Computer vision; Computers; Empirical analysis; Foundation models; Image analysis; Image processing; Image Processing, Computer-Assisted; Image segmentation; Internal Medicine; Language; Medical image segmentation; Medical imaging; Medicine; Natural Language Processing; Other; S-Adenosylmethionine; Segment anything model; Survey; Uncertainty; Survey; Foundation models; Segment anything model; Medical image segmentation
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108238

Due to the inherent flexibility of prompting, foundation models have emerged as the predominant force in the fields of natural language processing and computer vision. The recent introduction of the Segment Anything Model (SAM) signifies a noteworthy expansion of the prompt-driven paradigm into the domain of image segmentation, thereby introducing a plethora of previously unexplored capabilities. However, the viability of its application to medical image segmentation remains uncertain, given the substantial distinctions between natural and medical images. In this work, we provide a comprehensive overview of recent endeavors aimed at extending the efficacy of SAM to medical image segmentation tasks, encompassing both empirical benchmarking and methodological adaptations. Additionally, we explore potential avenues for future research directions in SAM’s role within medical image segmentation. While direct application of SAM to medical image segmentation does not yield satisfactory performance on multi-modal and multi-target medical datasets so far, numerous insights gleaned from these efforts serve as valuable guidance for shaping the trajectory of foundational models in the realm of medical image analysis. To support ongoing research endeavors, we maintain an active repository that contains an up-to-date paper list and a succinct summary of open-source projects at https://github.com/YichiZhang98/SAM4MIS. •The Segment Anything Model (SAM) signifies a noteworthy expansion of prompt-driven paradigm to image segmentation, but the viability of its application to medical images is uncertain..•We provide a comprehensive survey of recent endeavors aimed at extending the efficacy of SAM to medical image segmentation tasks.•We explore potential avenues for future research directions in SAM’s role within medical image segmentation.•We maintain an active repository that contains an up-to-date paper list and a succinct summary of open-source projects.