fMRI-Diffusion: Generating fMRI Time Series Via a Temporal Transformer Diffusion Model for Major Depressive Disorder Diagnosis
Researchers have developed fMRI-Diffusion, a novel framework that generates synthetic fMRI time series data to aid in the diagnosis of Major Depressive Disorder (MDD). Unlike previous methods that synthesize functional connectivity matrices, fMRI-Diffusion synthesizes region-of-interest level time series, preserving crucial temporal information. This approach, utilizing a Temporal Transformer within a diffusion model, has demonstrated consistent improvements in diagnostic accuracy across various classifiers and datasets, outperforming existing synthesis methods. AI
IMPACT This method could significantly improve the accuracy of AI-driven diagnostic tools for mental health conditions by addressing data scarcity.