{"slug": "fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion", "title": "fMRI-Diffusion: Generating fMRI Time Series Via a Temporal Transformer Diffusion Model for Major Depressive Disorder Diagnosis", "summary": "Researchers developed fMRI-Diffusion, a framework that generates synthetic fMRI time series using a Temporal Transformer diffusion model to improve Major Depressive Disorder diagnosis. The method outperformed existing augmentation techniques by preserving temporal brain activity patterns, achieving up to 3.7 percentage points higher diagnostic accuracy across multiple classifiers and datasets. This approach addresses the scarcity of labeled clinical fMRI data by producing realistic time series that enhance machine learning model training for MDD detection.", "body_md": "arXiv:2605.24065v1 Announce Type: new\nAbstract: Diagnosing Major Depressive Disorder (MDD) from functional magnetic resonance imaging (fMRI) using functional connectivity (FC) analysis requires large amounts of labeled data that are scarce in clinical settings. Existing augmentation methods synthesize FC matrices, which compress fMRI recordings into static pairwise summaries and discard temporal information. We propose fMRI-Diffusion, a framework that synthesizes region-of-interest (ROI)-level fMRI time series rather than FC matrices. A Temporal Transformer serves as the denoising network within a denoising diffusion probabilistic model, treating each time point as a token to capture temporal dependencies through self-attention. A supervised pretraining strategy initializes the Transformer with task-relevant representations before diffusion training, and FC matrices are derived from the synthesized time series for classification. Experiments on the REST-meta-MDD dataset show that augmenting training data with synthetic time series consistently improves diagnostic accuracy across ten classifiers, six parcellation atlases, and three acquisition sites. The method outperforms five recent FC-based synthesis approaches, with accuracy gains of up to 3.7 percentage points over the strongest baseline. Ablation studies confirm the contributions of both the Transformer-based denoiser and the pretraining strategy. Distributional fidelity metrics remain below 0.06 across all conditions, indicating close agreement between real and synthetic distributions. These findings suggest that synthesizing fMRI time series before FC computation preserves temporal information lost in matrix-level augmentation and provides a practical strategy for MDD diagnosis under limited data.", "url": "https://wpnews.pro/news/fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion", "canonical_source": "https://arxiv.org/abs/2605.24065", "published_at": "2026-05-26 04:00:00+00:00", "updated_at": "2026-05-26 04:12:21.244868+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "generative-ai", "artificial-intelligence", "ai-research"], "entities": ["Major Depressive Disorder", "fMRI-Diffusion", "Temporal Transformer", "REST-meta-MDD"], "alternates": {"html": "https://wpnews.pro/news/fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion", "markdown": "https://wpnews.pro/news/fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion.md", "text": "https://wpnews.pro/news/fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion.txt", "jsonld": "https://wpnews.pro/news/fmri-diffusion-generating-fmri-time-series-via-a-temporal-transformer-diffusion.jsonld"}}