Forecasting Alzheimer’s Disease Progression via Identity-preserved Denoising Diffusion Generative Adversarial Network
Preprint
- 28 November 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
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.Keywords
All Related Versions
- Version 1, 2025-11-28, Research Square
- Published version: npj Digital Medicine.
This publication has 28 references indexed in Scilit:
- Dual-layer cross-modal alignment recommendation based on the diffusion modelInformation Fusion, 2025
- Characterizing bidirectional transitions in mild cognitive impairment and post‐reversion based on longitudinal neuroimaging and cognitive assessmentsAlzheimer's & Dementia, 2025
- HiFi-Syn: Hierarchical granularity discrimination for high-fidelity synthesis of MR images with structure preservationMedical Image Analysis, 2024
- Metadata-conditioned generative models to synthesize anatomically-plausible 3D brain MRIsMedical Image Analysis, 2024
- Identifying underlying patterns in Alzheimer's disease trajectory: a deep learning approach and Mendelian randomization analysiseClinicalMedicine, 2023
- Different Regional Patterns in Gray Matter-based Age PredictionNeuroscience Bulletin, 2023
- The worldwide costs of dementia in 2019Alzheimer's & Dementia, 2023
- Deep image synthesis from intuitive user input: A review and perspectivesComputational Visual Media, 2022
- Predicting Alzheimer's disease progression using deep recurrent neural networksNeuroImage, 2020
- Sex differences in regional gray matter in healthy individuals aged 44–48 years: A voxel-based morphometric studyNeuroImage, 2007