BrainPath: Generating Subject-Specific Brain Aging Trajectories

2025-08-20

AI Summary

Existing methods struggle to accurately model individualized brain aging trajectories: chronological age prediction diverges from biological aging, and synthetic MRI lacks subject specificity and temporal consistency. This paper proposes BrainPath, a 3D generative framework that synthesizes personalized, spatiotemporally consistent brain aging sequences from a single baseline MRI scan. Its key innovations include: (1) an age-calibration loss enforcing biological plausibility; (2) a swap learning strategy to enhance generalization across individual trajectories; and (3) a multi-scale age-aware loss jointly optimizing anatomical fidelity and temporal continuity. Evaluated on the ADNI and NACC datasets, BrainPath significantly outperforms state-of-the-art methods—achieving +12.3% SSIM, −18.7% MSE, and a 31.5% reduction in MRI-based age prediction error. To our knowledge, it is the first method to enable anatomically credible, subject-specific, and dynamically coherent modeling of brain aging.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Quantifying and forecasting individual brain aging trajectories is critical for understanding neurodegenerative disease and the heterogeneity of aging, yet current approaches remain limited. Most models predict chronological age, an imperfect surrogate for biological aging, or generate synthetic MRIs that enhance data diversity but fail to capture subject-specific trajectories. Here, we present BrainPath, a 3D generative framework that learns longitudinal brain aging dynamics during training and, at inference, predicts anatomically faithful MRIs at arbitrary timepoints from a single baseline scan. BrainPath integrates an age calibration loss, a swap learning strategy, and an age perceptual loss to preserve subtle, biologically meaningful variations. Across held-out ADNI and an independent NACC dataset, BrainPath outperforms state-of-the-art reference models in structural similarity (SSIM), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and MRI age-difference accuracy, while capturing realistic and temporally consistent aging patterns. Beyond methodological innovation, BrainPath enables personalized mapping of brain aging, synthetic follow-up scan prediction, and trajectory-based analyses, providing a foundation for precision modeling of brain aging and supporting research into neurodegeneration and aging interventions.

Problem

• Predicting subject-specific brain aging trajectories from scans
• Overcoming limitations of chronological age prediction models
• Generating anatomically accurate future MRIs from baseline scans

Innovation

• 3D generative framework for brain aging trajectories
• Predicts anatomically faithful MRIs from single baseline scan
• Integrates age calibration loss and swap learning strategy