FFCM-MRF: An accurate and generalizable cerebrovascular segmentation pipeline for humans and rhesus monkeys based on TOF-MRA

• Published in: Computers in biology and medicine 2024-03, Vol.170, p.107996, Article 107996
• Main Authors: Cui, Yue, Huang, Haibin, Liu, Jialu, Zhao, Mingyang, Li, Chengyi, Han, Xinyong, Luo, Na, Gao, Jinquan, Yan, Dong-Ming, Zhang, Chen, Jiang, Tianzi, Yu, Shan
• Format: Article
• Language: English
• Subjects: Algorithms; Alzheimer's disease; Angiography; Animals; Automation; Biomarkers; Blood vessels; Brain; Brain - blood supply; Brain - diagnostic imaging; Cerebral vessels; Clustering; Datasets; Deep learning; Field strength; Fields (mathematics); Generalization; Heterogeneity; Humans; Image processing; Image segmentation; Macaca mulatta; Magnetic resonance; Magnetic Resonance Angiography - methods; Magnetic Resonance Imaging; Markov random field; Medical imaging; Methods; Monkeys; Monkeys & apes; Morphology; Neighborhoods; Neurodegenerative diseases; Neuroimaging; Noise reduction; Optimization; Pial artery; Reproducibility of Results; Scanners; Segmentation; TOF-MRA; Unsupervised learning; Vascular diseases
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.107996

Cerebrovascular segmentation and quantification of vascular morphological features in humans and rhesus monkeys are essential for prevention, diagnosis, and treatment of brain diseases. However, current automated whole-brain vessel segmentation methods are often not generalizable to independent datasets, limiting their usefulness in real-world environments with their heterogeneity in participants, scanners, and species. In this study, we proposed an automated, accurate and generalizable segmentation method for magnetic resonance angiography images called FFCM-MRF. This method integrated fast fuzzy c-means clustering and Markov random field optimization by vessel shape priors and spatial constraints. We used a total of 123 human and 44 macaque MRA images scanned at 1.5 T, 3 T, and 7 T MRI from 9 datasets to develop and validate the method. FFCM-MRF achieved average Dice similarity coefficients ranging from 69.16 % to 89.63 % across multiple independent datasets, with improvements ranging from 3.24 % to 7.3 % compared to state-of-the-art methods. Quantitative analysis showed that FFCM-MRF can accurately segment major arteries in the Circle of Willis at the base of the brain and small distal pial arteries while effectively reducing noise. Test-retest analysis showed that the model yielded high vascular volume and diameter reliability. Our results have demonstrated that FFCM-MRF is highly accurate and reliable and largely independent of variations in field strength, scanner platforms, acquisition parameters, and species. The macaque MRA data and user-friendly open-source toolbox are freely available at OpenNeuro and GitHub to facilitate studies of imaging biomarkers for cerebrovascular and neurodegenerative diseases. •Cerebrovascular segmentation was accomplished using FFCM-MRF.•FFCM-MRF refers to fast fuzzy c-means clustering with Markov random field refinement.•FFCM-MRF is a highly accurate, reliable, and generalizable method.•An open-source user-friendly toolbox is available to facilitate vascular studies.