Accelerating vision foundation model for efficient medical image segmentation
This study identifies two practical limitations when applying SAM to medical imaging: resizing low-resolution inputs to match the pre-trained scale and uniformly processing all patches, which lead to redundant computation. Therefore, we present an efficient strategy that integrates adapter-based tuning with token pausing to enhance throughput while preserving segmentation performance. Relevant codes and models of this paper will be available at https://github.com/wuwen1994/FasterSAM.
Authors
- Haichuan Song (ORCID: https://orcid.org/0000-0001-9867-836X)
- Weiyin Ma (ORCID: https://orcid.org/0000-0001-9760-7789)
- Xiao‐Diao Chen (ORCID: https://orcid.org/0000-0002-7523-7657)
- Xian‐Tao Wu
- Wu Wen (ORCID: https://orcid.org/0000-0001-7727-5043)
Institutions
- City University of Hong Kong (HK)
- Zhejiang University of Water Resource and Electric Power (CN)
- Hangzhou Dianzi University (CN)
- East China Normal University (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-12-19
- DOI
- https://doi.org/10.1002/mp.70193
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00