Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network

Forecasting the progression of Alzheimer’s disease (AD) is essential for evaluating secondary prevention measures thought to modify the disease trajectory. However, accurate prediction of longitudinal MRIs remains challenging, particularly in preserving subject identity, as deep generative models may potentially generate plausible future MRIs of different individuals from a single baseline scan. In the present study, we developed a novel identity-preserved denoising diffusion generative adversarial network (IP-DDGAN) capable of rapidly generating subject-specific longitudinal MRIs conditioned on metadata. Concretely, we developed an identity-preservation strategy with a metadata-guided module and identity-preserved regularization terms to maintain subject identity in synthetic longitudinal MRIs. Furthermore, we comprehensively integrated the morphometrics, subject identity consistency and image-level quality metrics to evaluate the fidelity and biological plausibility of synthetic longitudinal MRIs. The results demonstrate that the synthetic MRIs generated by IP-DDGAN retain biological and disease-related phenotypes, exhibiting sufficient realism to support their application in downstream tasks. Our proposed model is capable of capturing temporal biological and disease-related changes and forecasting the different progression trajectories, including critical transitions from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to AD.