SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation
This work addresses a crucial step in stroke diagnosis and surgical planning by enhancing segmentation accuracy for medical images with blurry boundaries and low contrast, though it is incremental as it builds on existing SAM-based methods.
The paper tackled the problem of adapting the Segment Anything Model (SAM) for intracranial hemorrhage segmentation, achieving improved performance on two public datasets through parameter-efficient fine-tuning and a combo loss.
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 .