Abstract
We compared the results of brain magnetic resonance image (MRI) segmentation across a longitudinal dataset spanning mouse adulthood using an atlas-based approach and deep learning. Our results demonstrate that deep learning performs similarly yet faster than more established segmentation methods, even when computational resources are limited. Both methods enabled the large-scale analysis of a cohort of C57Bl6/J healthy mice, revealing sex-dependent morphological differences in the aging brain. These findings highlight the potential use of deep learning for high-throughput, longitudinal neuroimaging studies and underscore the importance of considering sex as a biological variable in preclinical brain research.