Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity
The proposed deep learning model with a dissimilarity loss to reduce feature complexity effectively improves MRI-based identification of intracranial arterial calcification. It could help establish a more comprehensive and powerful pipeline for vascular image analysis on MRI.
Authors
- Huilin Zhao (ORCID: https://orcid.org/0000-0002-8490-4757)
- Chun Yuan (ORCID: https://orcid.org/0000-0002-6154-5106)
- Thomas S. Hatsukami
- Niranjan Balu (ORCID: https://orcid.org/0000-0002-1489-6683)
- Gádor Cantón (ORCID: https://orcid.org/0000-0002-0594-2764)
- Yan Zhou (ORCID: https://orcid.org/0000-0002-1659-1672)
- Yin Guo (ORCID: https://orcid.org/0000-0002-6006-9849)
- Linda G. Shapiro (ORCID: https://orcid.org/0000-0002-9495-0968)
- Mahmud Mossa‐Basha (ORCID: https://orcid.org/0000-0001-7798-8158)
- Ebru Yaman Akçiçek (ORCID: https://orcid.org/0000-0002-2413-0542)
- Halit Akçiçek (ORCID: https://orcid.org/0009-0006-4341-1856)
- Xin Wang (ORCID: https://orcid.org/0000-0001-9546-6038)
- Jin Zhang (ORCID: https://orcid.org/0000-0003-4152-521X)
- Beibei Sun (ORCID: https://orcid.org/0000-0002-2163-4163)
- Kaiyu Zhang (ORCID: https://orcid.org/0000-0001-7208-3114)
Institutions
- Shanghai Jiao Tong University (CN)
- University of Washington (US)
- University of Utah (US)
- Renji Hospital (CN)
- Paul G. Allen Family Foundation (US)
- University of Washington Applied Physics Laboratory (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2024-09-02
- DOI
- https://doi.org/10.1002/mrm.30283
- Citations
- 3
- Primary Topic
- Cerebrovascular and Carotid Artery Diseases
- Type
- article
- Field-Weighted Citation Impact
- 1.26
Funders
- National Institutes of Health