SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation

TL;DR

SAMIHS is a novel fine-tuning approach for the Segment Anything Model, tailored for intracranial hemorrhage segmentation, improving boundary recognition and performance on medical images with irregular regions.

Contribution

It introduces parameter-refactoring adapters and a combo loss to adapt SAM for medical image segmentation, specifically intracranial hemorrhage.

Findings

Effective on two public datasets

Improves boundary detection in hemorrhage segmentation

Outperforms baseline models

Abstract

Segment Anything Model (SAM), a vision foundation model trained on large-scale annotations, has recently continued raising awareness within medical image segmentation. Despite the impressive capabilities of SAM on natural scenes, it struggles with performance decline when confronted with medical images, especially those involving blurry boundaries and highly irregular regions of low contrast. In this paper, a SAM-based parameter-efficient fine-tuning method, called SAMIHS, is proposed for intracranial hemorrhage segmentation, which is a crucial and challenging step in stroke diagnosis and surgical planning. Distinguished from previous SAM and SAM-based methods, SAMIHS incorporates parameter-refactoring adapters into SAM's image encoder and considers the efficient and flexible utilization of adapters' parameters. Additionally, we employ a combo loss that combines binary cross-entropy loss and boundary-sensitive loss to enhance SAMIHS's ability to recognize the boundary regions. Our experimental results on two public datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/mileswyn/SAMIHS .