Temporally-Aware Diffusion Model for Brain Progression Modelling with Bidirectional Temporal Regularisation

2025-09-03

AI Summary

Existing MRI longitudinal prediction methods struggle to explicitly model the relationship between structural changes and inter-scan intervals, and are constrained by 2D architectures and limited clinical interpretability. To address these limitations, we propose TADM-3D—the first 3D time-aware diffusion model for brain structural dynamics modeling. Our method introduces: (1) a brain-age estimator as an anatomy-time joint guidance signal; (2) a bidirectional time regularization (BITR) mechanism enforcing temporal monotonicity and pathological evolution consistency in generated outputs; and (3) end-to-end modeling of whole-brain 3D anatomical context. Evaluated on OASIS-3 and NACC datasets, TADM-3D significantly improves the realism and temporal fidelity of future MRI synthesis. Generated images reliably reflect atrophy and lesion progression across varying time intervals, demonstrate strong cross-dataset generalization, and establish a novel paradigm for personalized prediction of neurodegenerative disease progression.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Generating realistic MRIs to accurately predict future changes in the structure of brain is an invaluable tool for clinicians in assessing clinical outcomes and analysing the disease progression at the patient level. However, current existing methods present some limitations: (i) some approaches fail to explicitly capture the relationship between structural changes and time intervals, especially when trained on age-imbalanced datasets; (ii) others rely only on scan interpolation, which lack clinical utility, as they generate intermediate images between timepoints rather than future pathological progression; and (iii) most approaches rely on 2D slice-based architectures, thereby disregarding full 3D anatomical context, which is essential for accurate longitudinal predictions. We propose a 3D Temporally-Aware Diffusion Model (TADM-3D), which accurately predicts brain progression on MRI volumes. To better model the relationship between time interval and brain changes, TADM-3D uses a pre-trained Brain-Age Estimator (BAE) that guides the diffusion model in the generation of MRIs that accurately reflect the expected age difference between baseline and generated follow-up scans. Additionally, to further improve the temporal awareness of TADM-3D, we propose the Back-In-Time Regularisation (BITR), by training TADM-3D to predict bidirectionally from the baseline to follow-up (forward), as well as from the follow-up to baseline (backward). Although predicting past scans has limited clinical applications, this regularisation helps the model generate temporally more accurate scans. We train and evaluate TADM-3D on the OASIS-3 dataset, and we validate the generalisation performance on an external test set from the NACC dataset. The code will be available upon acceptance.

Problem

• Predicting future brain MRI changes with accurate time intervals
• Overcoming limitations of 2D methods by using 3D anatomical context
• Generating clinically useful future pathological progression scans

Innovation

• 3D diffusion model for brain MRI progression
• Brain-Age Estimator guides time-aware generation
• Bidirectional temporal regularisation improves accuracy