Dual branch segment anything model‐transformer fusion network for accurate breast ultrasound image segmentation
Our dual-branch network leverages the complementary strengths of Swin Transformer and SAM through a fusion mechanism, demonstrating superior breast ultrasound segmentation performance. Our code is publicly available at https://github.com/Skylanding/DSATNet.
Authors
- Liye Mei (ORCID: https://orcid.org/0000-0002-2555-9199)
- Du Wang (ORCID: https://orcid.org/0000-0002-0098-7613)
- Jin Huang (ORCID: https://orcid.org/0000-0002-9651-609X)
- Cheng Lei (ORCID: https://orcid.org/0000-0001-8439-4235)
- Jingwen Zhang (ORCID: https://orcid.org/0000-0002-3264-3014)
- Yimin Zhang (ORCID: https://orcid.org/0000-0002-9962-3608)
- Yu Li (ORCID: https://orcid.org/0000-0001-5144-6318)
- Jingwen Deng (ORCID: https://orcid.org/0000-0002-5340-4856)
- Lan Dong
Institutions
- Wuhan University (CN)
- City University of Hong Kong, Shenzhen Research Institute (CN)
- Suzhou Research Institute (CN)
- Renmin Hospital of Wuhan University (CN)
- Hubei University of Technology (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-03-19
- DOI
- https://doi.org/10.1002/mp.17751
- Citations
- 6
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 14.89
Funders
- National Natural Science Foundation of China