MA-SAM: Modality-agnostic SAM adaptation for 3D medical image segmentation

Cheng Chen, Juzheng Miao, Dufan Wu, Aoxiao Zhong, Zhiling Yan, Sekeun Kim, Jiang Hu, Zhengliang Liu, Lichao Sun, Xiang Li, Tianming Liu, Pheng-Ann Heng, Quanzheng Li

Abstract: Highlights•A parameter-efficient adaptation of SAM to various volumetric and video medical data.•A state-of-the-art segmentation performance on various medical imaging modalities.•A comprehensive evaluation shows outstanding generalization capability of our model.•A impressive performance improvement on tumor segmentation by leveraging prompts.