Carotid artery segmentation in computed tomography angiography (CTA) using multi-scale deep supervision with Swin-UNet and advanced data augmentation
This study introduced a novel DL-based method for automatic 3D carotid artery segmentation from CTA images. The integration of Swin transformers, deep supervision mechanisms, and innovative data augmentation techniques significantly enhanced the accuracy and robustness of segmentation. This method offers valuable support for the clinical diagnosis and treatment of CAD and exhibits great potential for future medical image segmentation.
Authors
- Zhaotong Li (ORCID: https://orcid.org/0000-0002-6947-0065)
- Huiqun Wu (ORCID: https://orcid.org/0000-0001-5837-6199)
- Hongmei Gu (ORCID: https://orcid.org/0000-0002-8572-5435)
- Hua Xie (ORCID: https://orcid.org/0000-0002-2682-3481)
- Mingjing Li (ORCID: https://orcid.org/0000-0002-5290-8104)
- Zhu Li (ORCID: https://orcid.org/0000-0002-8246-177X)
- Tianle Wang (ORCID: https://orcid.org/0009-0003-7003-0264)
Institutions
- Nantong University (CN)
- Affiliated Hospital of Nantong University (CN)
Publication Details
- Journal
- Quantitative Imaging in Medicine and Surgery
- Published
- 2025-04-01
- DOI
- https://doi.org/10.21037/qims-24-2087
- Citations
- 2
- Primary Topic
- Cerebrovascular and Carotid Artery Diseases
- Type
- article
- Field-Weighted Citation Impact
- 3.04