Align-cDAE: Alzheimer's Disease Progression Modeling with Attention-Aligned Conditional Diffusion Auto-Encoder

2026-03-02

AI Summary

Existing generative models struggle to effectively align non-imaging conditions with image features when simulating Alzheimer’s disease progression, resulting in insufficient anatomical fidelity. To address this limitation, this work proposes an attention-aligned conditional diffusion autoencoder that explicitly aligns multimodal conditions with image features and disentangles disease progression from subject-specific identity within a structured latent space. The method introduces an alignment objective that focuses on disease-relevant anatomical regions and designs decoupled latent subspaces to separately model progression dynamics and individual characteristics. Experimental results demonstrate that the proposed model significantly enhances both the anatomical plausibility of generated brain images and the controllability of disease-related regions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Generative AI framework-based modeling and prediction of longitudinal human brain images offer an efficient mechanism to track neurodegenerative progression, essential for the assessment of diseases like Alzheimer's. Among the existing generative approaches, recent diffusion-based models have emerged as an effective alternative to generate disease progression images. Incorporating multi-modal and non-imaging attributes as conditional information into diffusion frameworks has been shown to improve controllability during such generations. However, existing methods do not explicitly ensure that information from non-imaging conditioning modalities is meaningfully aligned with image features to introduce desirable changes in the generated images, such as modulation of progression-specific regions. Further, more precise control over the generation process can be achieved by introducing progression-relevant structure into the internal representations of the model, lacking in the existing approaches. To address these limitations, we propose a diffusion autoencoder-based framework for disease progression modeling that explicitly enforces alignment between different modalities. The alignment is enforced by introducing an explicit objective function that enables the model to focus on the regions exhibiting progression-related changes. Further, we devise a mechanism to better structure the latent representational space of the diffusion auto-encoding framework. Specifically, we assign separate latent subspaces for integrating progression-related conditions and retaining subject-specific identity information, allowing better-controlled image generation. These results demonstrate that enforcing alignment and better structuring of the latent representational space of diffusion auto-encoding framework leads to more anatomically precise modeling of Alzheimer's disease progression.

Problem

• Alzheimer's disease progression
• diffusion models
• multi-modal alignment
• latent representation
• conditional generation

Innovation

• diffusion autoencoder
• modality alignment
• latent space structuring
• Alzheimer's disease progression
• conditional generation