A method for automatic 3D vasculature segmentation in ex vivo MRI using synthetic data
Chiara Mauri, Etienne Chollet, Adam Willis, Aliyah Jama, Ammar Mahmood, Angelina Ream, Itzel Garcia, Malak Benlahcen, Sariya Wood, Stephanie J. Lin, Priyanka Onta, Nam B. Tran, Xiangrui Zeng, Caroline V. Magnain, Rogeny Herisse, Erendira Garcia Pallares, Malte Hoffmann, Bruce Fischl, Yaël Balbastre · Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025
Motivation: Cerebral vascular anatomy is involved in several diseases, but only the largest vessels can be routinely imaged in vivo. Ex vivo MRI offers an alternative at higher resolution (~100 μm) where more vessels are visible. However, it has poor signal-to-noise ratio and nonspecific contrast, and obtaining accurate vessels manual annotations is extremely difficult. Goal(s): Our goal was to develop a method for automatic 3D vessel segmentation in ex vivo MRI. Approach: To overcome the lack of vessels manual annotations, we trained a neural network on synthetic data. Results: The segmentation method tested on real ex vivo MRI images achieved human-level performance. Impact: Our method for 3D vessel segmentation in ex vivo MRI can be used to build a whole-brain vascular atlas, and study inter-subject variability. It can also be adapted to microscopy and neuropathology, and to other tubular structures (axons and fascicles).