Multi-class segmentation of knee MRI based on hybrid attention
These results demonstrate that the proposed hybrid attention and multi-scale strategy can effectively address the challenges of class imbalance in knee MRI images, improving the model's overall segmentation performance.
Authors
- Xinglin Zhang (ORCID: https://orcid.org/0000-0003-2592-6945)
- Yachen Xiang (ORCID: https://orcid.org/0000-0001-8111-6782)
- Tao Meng (ORCID: https://orcid.org/0000-0002-4355-990X)
- Tao Chen (ORCID: https://orcid.org/0000-0003-2725-6199)
Institutions
- Harvard University (US)
- University of Waterloo (CA)
- Gannan Medical University (CN)
- Jiangnan Industry Group (China) (CN)
- Intelligent Health (United Kingdom) (GB)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-06-11
- DOI
- https://doi.org/10.3389/fmed.2025.1581487
- Citations
- 3
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 3.83