DiGAN: Diffusion-Guided Attention Network for Early Alzheimer's Disease Detection

TL;DR

DiGAN introduces a novel diffusion-guided attention network that synthesizes neuroimaging trajectories and captures structural-temporal patterns, enhancing early Alzheimer's detection from limited data.

Contribution

The paper presents DiGAN, a new model combining diffusion modeling and attention mechanisms to improve early AD diagnosis with scarce longitudinal data.

Findings

Outperforms existing methods on ADNI dataset

Synthesizes realistic neuroimaging trajectories

Effective in early-stage AD detection

Abstract

Early diagnosis of Alzheimer's disease (AD) remains a major challenge due to the subtle and temporally irregular progression of structural brain changes in the prodromal stages. Existing deep learning approaches require large longitudinal datasets and often fail to model the temporal continuity and modality irregularities inherent in real-world clinical data. To address these limitations, we propose the Diffusion-Guided Attention Network (DiGAN), which integrates latent diffusion modelling with an attention-guided convolutional network. The diffusion model synthesizes realistic longitudinal neuroimaging trajectories from limited training data, enriching temporal context and improving robustness to unevenly spaced visits. The attention-convolutional layer then captures discriminative structural-temporal patterns that distinguish cognitively normal subjects from those with mild cognitive impairment and subjective cognitive decline. Experiments on the ADNI dataset demonstrate that DiGAN outperforms existing state-of-the-art baselines, showing its potential for early-stage AD detection.