Identifying Brain Regions Vulnerable and Resistant to Aging Using AI-Derived Cerebral Blood Volume from T1-Weighted MRI

Motivation: Aging impacts brain regions differently, leading to cognitive decline and vascular changes. Identifying the most susceptible or resilient regions is crucial for understanding neurodegeneration and developing interventions. Goal(s): To identify aging-sensitive and resilient brain regions by developing a pipeline generating AI-derived CBV (AICBV) maps from standard T1-weighted MRI. Approach: We used DeepContrast AI model to generate AICBV maps from T1-weighted MRI scans of 2,851 subjects. FreeSurfer provided segmentation for regional CBV analysis. Results: Dentate gyrus and inferior frontal gyrus subregions are highly vulnerable to aging; the entorhinal cortex shows resilience. Our findings align with prior studies, extending them to a larger cohort. Impact: This non-invasive AICBV mapping technique offers an efficient alternative to traditional CBV fMRI scans, enabling large-scale and longitudinal studies of brain aging. It allows early detection of high-risk regions and guides targeted interventions to preserve cognitive health and resilience.