Intracranial aneurysm segmentation with nnU-net: utilizing loss functions and automated vessel extraction
The proposed method offers a promising solution for accurately segmenting intracranial aneurysms, showcasing superior performance compared to existing approaches. By integrating hybrid loss functions and vessel information, we enhance the model's ability to delineate intricate aneurysm structures, contributing to improved diagnosis and treatment planning for patients with intracranial aneurysms.
Authors
- Maysam Orouskhani (ORCID: https://orcid.org/0000-0003-3341-3904)
- Negar Firoozeh (ORCID: https://orcid.org/0000-0002-5423-4406)
- Hanrui Shi
- Huayu Wang (ORCID: https://orcid.org/0000-0002-3773-680X)
- Mahmud Mossa‐Basha (ORCID: https://orcid.org/0000-0001-7798-8158)
- Yan Wang (ORCID: https://orcid.org/0000-0001-9152-0631)
- Chengcheng Zhu (ORCID: https://orcid.org/0000-0001-6898-549X)
- Beibei Sun (ORCID: https://orcid.org/0000-0002-2163-4163)
- Weijing Li (ORCID: https://orcid.org/0000-0001-7868-1342)
- Xiao Li (ORCID: https://orcid.org/0000-0002-2406-3781)
- Jianjian Zhang (ORCID: https://orcid.org/0000-0003-3485-0495)
- Jenq–Neng Hwang (ORCID: https://orcid.org/0000-0002-8877-2421)
- Huilin Zhao
Institutions
- University of California, San Francisco (US)
- University of Washington (US)
- Renji Hospital (CN)
- University of California System (US)
Publication Details
- Journal
- Vessel Plus
- Published
- 2025-12-10
- DOI
- https://doi.org/10.20517/2574-1209.2025.42
- Primary Topic
- Intracranial Aneurysms: Treatment and Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health