A segment anything model‐guided and match‐based semi‐supervised segmentation framework for medical imaging
Our SAM-Match framework shows promising results in semi-supervised semantic segmentation, effectively tackling the challenges of automatic prompt generation for SAM and high-quality pseudo-label generation for Match-based models. It can help accelerate the adoption of semi-supervised learning in segmentation tasks, particularly in data-scarce scenarios. Our data and code will be made available at https://github.com/apple1986/SAMatch.
Authors
- Xiaoxue Qian (ORCID: https://orcid.org/0000-0002-6185-1074)
- Weiguo Lu (ORCID: https://orcid.org/0000-0003-3036-7287)
- Jiaming Luo (ORCID: https://orcid.org/0000-0003-0025-0379)
- You Zhang (ORCID: https://orcid.org/0000-0002-8033-2755)
- Guoping Xu (ORCID: https://orcid.org/0000-0001-8932-3321)
- Hua‐Chieh Shao (ORCID: https://orcid.org/0009-0003-7664-7257)
Institutions
- Harvard University (US)
- Massachusetts General Hospital (US)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-03-29
- DOI
- https://doi.org/10.1002/mp.17785
- Citations
- 6
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 7.66