Evaluation of a Rapid and Practical Deep Learning Framework for T1-weighted MRI-based Brain Age Estimation

Purpose To develop and evaluate a rapid brain-age estimation framework using freely available Python tools and assess the clinical relevance of brain-age gap (BAG). Materials and Methods In this retrospective study conducted from March 2025 to August 2026, T1-weighted MR images from cohorts of cognitively normal adults ( n = 4,346) were divided into training, validation, and internal test sets; two cohorts ( n = 315 and 209) served as external test sets. Clinical evaluation used the BICWALZS cohort ( n = 954; cognitively normal and various dementias). Preprocessing used freely available Python tools only. The model was trained to predict chronological age as the reference standard. Associations of the residualized BAG with diagnosis, amyloid PET positivity, white matter hyperintensity (WMH) severity, stroke history, and longitudinal clinical worsening were evaluated using ANCOVA, logistic regression, and Cox models. Results The development cohort included 4,346 cognitively normal adults (mean age, 47.0 ± 21.2 years; 2,414 women). Chronological age prediction yielded R 2 = 0.95 and MAE, 3.76 years in the internal test set and R 2 = 0.69–0.90 and MAE, 4.82–5.15 years in external test sets. The residualized BAG increased across diagnostic groups ( P < .001) and was associated with WMH severity (odds ratio [OR], 1.64; P < .001) and stroke history (OR, 1.46; P < .001), but not with amyloid positivity after full adjustment ( P = .17), and predicted longitudinal clinical worsening (HR, 1.92). Conclusion The framework accurately predicted age, while residualized BAG was associated with diagnosis, cerebrovascular burden, and longitudinal clinical worsening. © RSNA, 2026