Abstract
Precision neuroimaging aims to deliver individualized assessments of brain health, yet a single structural MRI does not provide a scalable, multidimensional, quantitative summary of an individual's current or future health. Existing approaches optimize task-specific objectives, yielding representations entangled with cohort- or disease-specific signals rather than capturing biologically grounded anatomical patterns. Here, we introduce NeuroFM, a foundation model trained exclusively on 100,000 healthy synthetic volumes to predict morphometric and demographic targets. Without exposure to disease-labelled data, NeuroFM organizes brain structure into population-level patterns encoding brain health differences. These representations transfer across neuroscience domains without adaptation and support simple linear readouts for clinical, cognitive, developmental, socio-behavioural, and image quality. Evaluated on 136,361 multi-cohort volumes, NeuroFM generalizes across domains and enables individual-level brain health profiling, estimating future dementia risk years before diagnosis. Together, these findings establish a disease-naïve foundation model for precision neuroimaging with potential to support quantitative brain health assessments across settings.