Conditional Diffusion Model for Longitudinal Medical Image Generation
This addresses data scarcity issues for researchers studying Alzheimer's disease progression, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of missing and irregular longitudinal medical imaging data in Alzheimer's disease by proposing a diffusion-based model that generates 3D longitudinal images from a single MRI, with results showing higher-quality images compared to other methods.
Alzheimers disease progresses slowly and involves complex interaction between various biological factors. Longitudinal medical imaging data can capture this progression over time. However, longitudinal data frequently encounter issues such as missing data due to patient dropouts, irregular follow-up intervals, and varying lengths of observation periods. To address these issues, we designed a diffusion-based model for 3D longitudinal medical imaging generation using single magnetic resonance imaging (MRI). This involves the injection of a conditioning MRI and time-visit encoding to the model, enabling control in change between source and target images. The experimental results indicate that the proposed method generates higher-quality images compared to other competing methods.