Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30283 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Xin Wang und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of Washington, Seattle, Washington. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NINDS NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Purpose
To develop an automated deep learning model for MRI‐based segmentation and detection of intracranial arterial calcification.
Methods
A novel deep learning model under the variational autoencoder framework was developed. A theoretically grounded dissimilarity loss was proposed to refine network features extracted from MRI and restrict their complexity, enabling the model to learn more generalizable MR features that enhance segmentation accuracy and robustness for detecting calcification on MRI.
Results
The proposed method was compared with nine baseline methods on a dataset of 113 subjects and showed superior performance (for segmentation, Dice similarity coefficient: 0.620, area under precision‐recall curve [PR‐AUC]: 0.660, 95% Hausdorff Distance: 0.848 mm, Average Symmetric Surface Distance: 0.692 mm; for slice‐wise detection, F1 score: 0.823, recall: 0.764, precision: 0.892, PR‐AUC: 0.853). For clinical needs, statistical tests confirmed agreement between the true calcification volumes and predicted values using the proposed approach. Various MR sequences, namely T1, time‐of‐flight, and SNAP, were assessed as inputs to the model, and SNAP provided unique and essential information pertaining to calcification structures.
Conclusion
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, University of Washington, Seattle, Washington.
- Vascular Imaging Lab, Department of Radiology, University of Washington, Seattle, Washington.
- Department of Bioengineering, University of Washington, Seattle, Washington.
- Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah.
- Department of Surgery, University of Washington, Seattle, Washington.
- Department of Radiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
ORCID-Profile: Xin Wang, Ebru Yaman Akcicek, Chun Yuan
Förderung
- NIH HHS
- NINDS NIH HHS
- National Institutes of Health
Zitieren
APA
Wang, X., Canton, G., Guo, Y., Zhang, K., Akcicek, H., Yaman Akcicek, E., Hatsukami, T., Zhang, J., Sun, B., Zhao, H., Zhou, Y., Shapiro, L., Mossa-Basha, M., Yuan, C., & Balu, N. (2025). Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30283
Vancouver
Wang X, Canton G, Guo Y, Zhang K, Akcicek H, Yaman Akcicek E, et al. Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30283
BibTeX
@article{Wang2025,
author = {Wang, Xin and Canton, Gador and Guo, Yin and Zhang, Kaiyu and Akcicek, Halit and Yaman Akcicek, Ebru and Hatsukami, Thomas and Zhang, Jin and Sun, Beibei and Zhao, Huilin and Zhou, Yan and Shapiro, Linda and Mossa-Basha, Mahmud and Yuan, Chun and Balu, Niranjan},
title = {Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30283}
}
EUVIMED