Scalable Diffusion Transformer for Conditional 4D fMRI Synthesis
This work provides a practical method for conditional 4D fMRI synthesis, enabling applications like virtual experiments and neuroimaging augmentation, though it is incremental in combining existing techniques.
The paper tackled the challenge of generating whole-brain 4D fMRI sequences conditioned on cognitive tasks by introducing a diffusion transformer model, which achieved a task-evoked map correlation of 0.83 and RSA of 0.98 on HCP task fMRI data.
Generating whole-brain 4D fMRI sequences conditioned on cognitive tasks remains challenging due to the high-dimensional, heterogeneous BOLD dynamics across subjects/acquisitions and the lack of neuroscience-grounded validation. We introduce the first diffusion transformer for voxelwise 4D fMRI conditional generation, combining 3D VQ-GAN latent compression with a CNN-Transformer backbone and strong task conditioning via AdaLN-Zero and cross-attention. On HCP task fMRI, our model reproduces task-evoked activation maps, preserves the inter-task representational structure observed in real data (RSA), achieves perfect condition specificity, and aligns ROI time-courses with canonical hemodynamic responses. Performance improves predictably with scale, reaching task-evoked map correlation of 0.83 and RSA of 0.98, consistently surpassing a U-Net baseline on all metrics. By coupling latent diffusion with a scalable backbone and strong conditioning, this work establishes a practical path to conditional 4D fMRI synthesis, paving the way for future applications such as virtual experiments, cross-site harmonization, and principled augmentation for downstream neuroimaging models.