A method for automatic 3D vasculature segmentation in ex vivo MRI using synthetic data
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).
Authors
- Ammar Mahmood (ORCID: https://orcid.org/0000-0002-8553-3935)
- Stephen R. Wood
- Bruce Fischl
- Caroline Magnain (ORCID: https://orcid.org/0000-0003-4244-7380)
- Etienne Chollet
- Erendira Garcia Pallares (ORCID: https://orcid.org/0000-0003-1524-6698)
- I. García (ORCID: https://orcid.org/0000-0002-1138-2118)
- Stephanie J. Lin
- Xiangrui Zeng (ORCID: https://orcid.org/0000-0002-8589-4474)
- Adam M. Willis (ORCID: https://orcid.org/0000-0001-8088-523X)
- Yaël Balbastre (ORCID: https://orcid.org/0000-0001-8758-9978)
- Rogeny Herisse
- Chiara Mauri (ORCID: https://orcid.org/0000-0002-4928-9744)
- Malte Hoffmann (ORCID: https://orcid.org/0000-0002-5511-0739)
- Nam Tran (ORCID: https://orcid.org/0009-0004-8955-3169)
- Priyanka Onta
- Aliyah Jama
- Angelina Ream
- Malak Benlahcen
Publication Details
- Journal
- 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
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/1054
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00