Neural Autoregressive Modeling of Brain Aging

2025-07-29

AI Summary

This study addresses the challenge of modeling individual brain structural aging trajectories from early MRI scans, capturing dynamic neuroaging processes amid high-dimensional data, subtle cross-age anatomical changes, and substantial inter-individual heterogeneity. To this end, we propose NeuroAR—the first generative autoregressive Transformer model tailored for brain aging modeling. NeuroAR discretizes brain structural representations into tokens, incorporates a time-aware cross-attention mechanism to integrate longitudinal scan timing information, and employs forward–backward token embeddings to guide conditional generation. Evaluated on adolescent and elderly cohorts, NeuroAR significantly outperforms latent diffusion models and GANs in both image fidelity and biological plausibility of predicted aging patterns, achieving state-of-the-art performance. The framework establishes a novel paradigm for personalized neuroaging modeling and informs clinically actionable interventions.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Brain aging synthesis is a critical task with broad applications in clinical and computational neuroscience. The ability to predict the future structural evolution of a subject's brain from an earlier MRI scan provides valuable insights into aging trajectories. Yet, the high-dimensionality of data, subtle changes of structure across ages, and subject-specific patterns constitute challenges in the synthesis of the aging brain. To overcome these challenges, we propose NeuroAR, a novel brain aging simulation model based on generative autoregressive transformers. NeuroAR synthesizes the aging brain by autoregressively estimating the discrete token maps of a future scan from a convenient space of concatenated token embeddings of a previous and future scan. To guide the generation, it concatenates into each scale the subject's previous scan, and uses its acquisition age and the target age at each block via cross-attention. We evaluate our approach on both the elderly population and adolescent subjects, demonstrating superior performance over state-of-the-art generative models, including latent diffusion models (LDM) and generative adversarial networks, in terms of image fidelity. Furthermore, we employ a pre-trained age predictor to further validate the consistency and realism of the synthesized images with respect to expected aging patterns. NeuroAR significantly outperforms key models, including LDM, demonstrating its ability to model subject-specific brain aging trajectories with high fidelity.

Problem

• Predict future brain structure evolution from MRI scans
• Address high-dimensional data and subtle aging changes
• Model subject-specific brain aging patterns accurately

Innovation

• Generative autoregressive transformers for brain aging
• Concatenated token embeddings guide future scan synthesis
• Cross-attention integrates previous scan and target age