A segmentation method for oral CBCT image based on Segment Anything Model and semi‐supervised teacher‐student model
SAM-TS outperforms existing semi-supervised methods, offering a more competitive and efficient approach to CBCT image segmentation. This method addresses the data annotation bottleneck and opens new avenues for semi-supervised learning applications in medical imaging.
Authors
- Tongli He
- Runqing Kang
- Xun Deng (ORCID: https://orcid.org/0009-0004-3613-864X)
- Yuling Gan
- Xiangyi Chen (ORCID: https://orcid.org/0000-0001-5549-5336)
- Peiyang Wei (ORCID: https://orcid.org/0009-0008-9632-8006)
- Nie Yu (ORCID: https://orcid.org/0009-0004-2609-7768)
- Xiaoli Peng (ORCID: https://orcid.org/0000-0002-3436-2574)
- Zhibin Li (ORCID: https://orcid.org/0000-0002-0501-2305)
Institutions
- Chongqing University of Posts and Telecommunications (CN)
- China Meteorological Administration (CN)
- Jilin University (CN)
- Chinese Academy of Sciences (CN)
- Chengdu University of Information Technology (CN)
- Sichuan University of Arts and Science (CN)
- Xinjiang Technical Institute of Physics & Chemistry (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-05-07
- DOI
- https://doi.org/10.1002/mp.17854
- Citations
- 2
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.35
Funders
- Sichuan Province Science and Technology Support Program