Doelemeyer, Arno, Vaishampayan, Saurabh, Zurbruegg, Stefan, Morvan, Frederic, Locatelli, Giuseppe, Shimshek, Derya and Beckmann, Nicolau (2025) Deep Learning-Driven MRI for Accurate Brain Volumetry in Murine Models of Neurodegenerative Diseases. Frontiers in neuroscience, 19. p. 1632169.

Abstract

Brain atrophy as assessed by magnetic resonance imaging (MRI) is a key measure of neurodegeneration and a predictor of disability progression in Alzheimer’s disease and multiple sclerosis (MS) patients. While MRI-based brain volumetry is valuable for analyzing neurodegeneration in murine models as well, achieving high spatial resolution at sufficient signal-to-noise ratio is challenging due to the small size of the mouse brain. Ex vivo analysis offers greater resolution but is limited by potential tissue distortions and shrinkage due to preparation processes. In vivo imaging allows for longitudinal studies and repeated assessments, enhancing statistical power and enabling pharmacological evaluations. However, the need for anesthesia necessitates compromises in acquisition times and voxel sizes. We demonstrate the application of deep learning for reliable quantification of brain region volumes, such as the hippocampus, caudate putamen, and cerebellum, from T2-weighted images with a pixel volume of 78x78x250 µm³ acquired in 4.3 minutes at 7 Tesla. The reproducibility of the fully automatic segmentation pipeline was validated in healthy C57BL/6J mice and subsequently applied to models of amyotrophic lateral sclerosis, cuprizone-induced demyelination, and MS. Our approach offers a robust and efficient method for in vivo brain volumetry in preclinical mouse studies, facilitating the evaluation of neurodegenerative processes and therapeutic interventions. The dramatic reduction in acquisition time achieved with our AI-based approach significantly enhances animal welfare (3R). This advancement allows brain volumetry to be seamlessly integrated into additional analyses, providing comprehensive insights without substantially increasing study duration.

Item Type:	Article
Keywords:	3R, amyotrophic lateral sclerosis (ALS), artificial intelligence, deep learning, magnetic resonance imaging (MRI), multiple sclerosis (MS), neurodegeneration, volumetry
Date Deposited:	18 Nov 2025 00:45
Last Modified:	18 Nov 2025 00:45
URI:	https://oak.novartis.com/id/eprint/56992