Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion

2025-02-12

AI Summary

To address key challenges in personalized progression prediction for neurodegenerative diseases—including patient-specific modeling, spatiotemporal consistency preservation, effective longitudinal data utilization, and high memory overhead of 3D MRI—we propose the first latent-space diffusion framework tailored for 3D brain MRI. Methodologically, we introduce metadata-conditioned injection for patient-specific modeling; design a prior-guided auxiliary model to enhance biological plausibility; and propose Latent Average Stabilization (LAS), an algorithm that explicitly enforces spatiotemporal consistency and quantifies prediction uncertainty. Trained on 11,730 MRI scans from 2,805 subjects, our framework achieves state-of-the-art performance on an external test set comprising 2,257 scans from 962 subjects, significantly outperforming existing methods across all major metrics.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Computer Vision: Diffusion Models for Vision
• Humans and AI: Brain-Sensing and Analysis

Application Category

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

Abstract

The growing availability of longitudinal Magnetic Resonance Imaging (MRI) datasets has facilitated Artificial Intelligence (AI)-driven modeling of disease progression, making it possible to predict future medical scans for individual patients. However, despite significant advancements in AI, current methods continue to face challenges including achieving patient-specific individualization, ensuring spatiotemporal consistency, efficiently utilizing longitudinal data, and managing the substantial memory demands of 3D scans. To address these challenges, we propose Brain Latent Progression (BrLP), a novel spatiotemporal model designed to predict individual-level disease progression in 3D brain MRIs. The key contributions in BrLP are fourfold: (i) it operates in a small latent space, mitigating the computational challenges posed by high-dimensional imaging data; (ii) it explicitly integrates subject metadata to enhance the individualization of predictions; (iii) it incorporates prior knowledge of disease dynamics through an auxiliary model, facilitating the integration of longitudinal data; and (iv) it introduces the Latent Average Stabilization (LAS) algorithm, which (a) enforces spatiotemporal consistency in the predicted progression at inference time and (b) allows us to derive a measure of the uncertainty for the prediction. We train and evaluate BrLP on 11,730 T1-weighted (T1w) brain MRIs from 2,805 subjects and validate its generalizability on an external test set comprising 2,257 MRIs from 962 subjects. Our experiments compare BrLP-generated MRI scans with real follow-up MRIs, demonstrating state-of-the-art accuracy compared to existing methods. The code is publicly available at: https://github.com/LemuelPuglisi/BrLP.

Problem

• Predicts individual disease progression
• Ensures spatiotemporal consistency
• Reduces 3D MRI computational demands

Innovation

• Utilizes latent space for computational efficiency
• Integrates metadata for personalized predictions
• Enforces spatiotemporal consistency with LAS algorithm