A segmentation method for cardiac MRI that incorporates region constraint guidance and tubular structure awareness within a Siamese network architecture
The proposed RCSiamTANet significantly enhances the segmentation performance of complex cardiac structural regions and tubular structures, effectively improving both accuracy and generalization.
Authors
- Jiangting Wang (ORCID: https://orcid.org/0000-0002-8171-6291)
- Hui Yang (ORCID: https://orcid.org/0000-0002-8040-2792)
- Qiaohong Liu (ORCID: https://orcid.org/0009-0009-7637-8185)
- Xinyu Li (ORCID: https://orcid.org/0000-0002-3730-0360)
- Chuanqing Zhou (ORCID: https://orcid.org/0000-0002-9030-4993)
- Keyan Chen (ORCID: https://orcid.org/0000-0003-0483-1306)
Institutions
- University of Shanghai for Science and Technology (CN)
- Shanghai University of Medicine and Health Sciences (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-11-27
- DOI
- https://doi.org/10.1002/mp.70172
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China