Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
This work addresses the problem of adapting general-purpose segmentation models to medical images for researchers and practitioners in medical imaging, representing an incremental improvement by building on SAM with lightweight modifications.
The paper tackles the underperformance of the Segment Anything Model (SAM) in medical image segmentation by proposing the Medical SAM Adapter (Med-SA), which adapts SAM using domain-specific knowledge and achieves state-of-the-art results on 17 medical image segmentation tasks while updating only 2% of the parameters.
The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation due to its impressive capabilities in various segmentation tasks and its prompt-based interface. However, recent studies and individual experiments have shown that SAM underperforms in medical image segmentation, since the lack of the medical specific knowledge. This raises the question of how to enhance SAM's segmentation capability for medical images. In this paper, instead of fine-tuning the SAM model, we propose the Medical SAM Adapter (Med-SA), which incorporates domain-specific medical knowledge into the segmentation model using a light yet effective adaptation technique. In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation. We conduct comprehensive evaluation experiments on 17 medical image segmentation tasks across various image modalities. Med-SA outperforms several state-of-the-art (SOTA) medical image segmentation methods, while updating only 2\% of the parameters. Our code is released at https://github.com/KidsWithTokens/Medical-SAM-Adapter.