Intracranial aneurysm segmentation on digital subtraction angiography: a retrospective and multi-center study
Our proposed SDAN significantly improves the accurate segmentation of intracranial aneurysms in DSA images beyond existing medical image segmentation models. The model solves the problems of small intracranial aneurysms that are not easily segmented accurately, over-segmentation caused by the similarity of intracranial aneurysms and ring vessels, and under-segmentation caused by the overlap of neighboring vessels.
Authors
- Jing Li (ORCID: https://orcid.org/0000-0002-2052-9302)
- Ruibo Liu (ORCID: https://orcid.org/0000-0002-8813-0752)
- Guangxin Chu
- He Ma (ORCID: https://orcid.org/0000-0002-5054-3586)
- Guobiao Liang
- Ligang Chen (ORCID: https://orcid.org/0000-0002-5025-2842)
- Wei Qian
- Hai Jin (ORCID: https://orcid.org/0000-0002-1194-9778)
- Ruixuan Zhang (ORCID: https://orcid.org/0009-0009-2452-884X)
Institutions
- Fourth Affiliated Hospital of China Medical University (CN)
- General Hospital of Shenyang Military Region (CN)
- China Medical University (CN)
- Northeastern University (CN)
Publication Details
- Journal
- Frontiers in Neurology
- Published
- 2025-10-13
- DOI
- https://doi.org/10.3389/fneur.2025.1646517
- Primary Topic
- Intracranial Aneurysms: Treatment and Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00