Neuroinformatics · Apr 24, 2026
Corpus Callosum Segmentation on Structural MRI Using Multi-atlas Deformable Registration
By Sariaslani A, Abrishami Moghaddam H, A Ardekani B et al.
The corpus callosum (CC), the largest white matter structure in the brain, exhibits morphological changes in normal aging and neurodegenerative disorders. A reliable CC segmentation method facilitates early detection and monitoring of neurological disorders such as Alzheimer’s disease (AD). This study presents Yuki, a fully automated CC segmentation program, evaluates its performance, and demonstrates its utility in structural MRI analysis. We describe an automated method for CC segmentation on structural MRI using multi-atlas deformable registration. Accuracy is assessed in 90 participants using the Dice Similarity Coefficient (DSC). Cross-sectionally, 100 cognitively normal (CN) and 100 AD participants are compared in CC area, circularity, and thickness. Longitudinally, test-retest reliability is evaluated in 49 participants with back-to-back scans, and CC circularity decline is analyzed over two years in 62 CN and 55 AD participants. Yuki achieved a DSC of 97.4% on the test set and 98.2% in the test-retest analysis. Cross-sectionally, CC area, circularity, and thickness were significantly reduced in AD compared to CN (p < .001, p < .0001, p < 10⁻6). Point-wise analysis showed diffuse CC thinning in AD except at the isthmus. CC circularity declined significantly over two years in both CN and AD, with a faster rate in AD (p < 10⁻15, p < 10⁻15, p < 10⁻4). Yuki provides accurate, reliable, and reproducible CC segmentation for 3D MRI. Its application in AD highlights its utility in neurodegenerative research, where declines in CC thickness and circularity can serve as structural biomarkers of interest.