Scalable Diffusion Transformer for Conditional 4D fMRI Synthesis

• URL: http://arxiv.org/abs/2511.22870v1
• Date: Fri, 28 Nov 2025 04:18:11 GMT
• Title: Scalable Diffusion Transformer for Conditional 4D fMRI Synthesis
• Authors: Jungwoo Seo, David Keetae Park, Shinjae Yoo, Jiook Cha,
• Abstract summary: We introduce the first diffusion transformer for voxelwise 4D fMRI conditional generation.<n>On task fMRI, our model reproduces task-evoked activation maps, preserves the inter-task representational structure, and achieves perfect condition specificity.<n>Performance improves predictably with scale, reaching task-evoked map correlation of 0.83 and RSA of 0.98.
• Score: 13.638452834334982
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Subtractive Modulative Network with Learnable Periodic Activations [59.89799070130572]
  We propose a novel, parameter-efficient Implicit Neural Representation architecture inspired by classical subtractive synthesis.<n>Our SMN achieves a PSNR of $40+$ dB on two image datasets, comparing favorably against state-of-the-art methods in terms of both reconstruction accuracy and parameter efficiency.
  arXiv  Detail & Related papers  (2026-02-18T10:20:50Z)
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction [65.67001243986981]
  We propose MindHier, a coarse-to-fine fMRI-to-image reconstruction framework built on scale-wise autoregressive modeling.<n>MindHier achieves superior semantic fidelity, 4.67x faster inference, and more deterministic results than the diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-10-25T15:40:07Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• NeuroRVQ: Multi-Scale EEG Tokenization for Generative Large Brainwave Models [66.91449452840318]
  We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer.<n>Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training.<n>Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks.
  arXiv  Detail & Related papers  (2025-10-15T01:26:52Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Rest2Visual: Predicting Visually Evoked fMRI from Resting-State Scans [30.743554598059692]
  We introduce Rest2Visual, a conditional generative model that predicts visually evoked fMRI (ve-fMRI) from resting-state input and 2D visual stimuli.<n>Our results provide compelling evidence that individualized spontaneous neural activity can be transformed into stimulus-aligned representations.
  arXiv  Detail & Related papers  (2025-09-17T01:08:03Z)
• SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning [54.390403684665834]
  Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience.<n>We propose SynBrain, a generative framework that simulates the transformation from visual semantics to neural responses in a probabilistic and biologically interpretable manner.<n> Experimental results demonstrate that SynBrain surpasses state-of-the-art methods in subject-specific visual-to-fMRI encoding performance.
  arXiv  Detail & Related papers  (2025-08-14T03:01:05Z)
• A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation [1.662610796043078]
  Transcranial focused ultrasound (tFUS) is an emerging modality for non-invasive brain stimulation and therapeutic intervention.<n>TFUScapes is the first large-scale, high-resolution dataset of tFUS simulations through anatomically realistic human skulls.<n>DeepTFUS is a deep learning model that estimates normalized pressure fields directly from input 3D CT volumes and transducer position.
  arXiv  Detail & Related papers  (2025-05-19T11:37:51Z)
• X$^{2}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction [64.2059940799033]
  Current methods discretize temporal resolution into fixed phases with respiratory gating devices.<n>X$2$-Gaussian, a novel framework, enables continuous-time 4DCT reconstruction by integrating dynamic radiative splatting with self-supervised respiratory motion learning.
  arXiv  Detail & Related papers  (2025-03-27T17:59:57Z)
• fMRI-S4: learning short- and long-range dynamic fMRI dependencies using 1D Convolutions and State Space Models [0.0]
  fMRI-S4 is a versatile deep learning model for the classification of phenotypes and psychiatric disorders from resting-state functional magnetic resonance imaging scans. We show that fMRI-S4 can outperform existing methods on all three tasks and can be trained as a plug&play model without special hyperpararameter tuning for each setting.
  arXiv  Detail & Related papers  (2022-08-08T14:07:25Z)
• Attend and Decode: 4D fMRI Task State Decoding Using Attention Models [2.6954666679827137]
  We present a novel architecture called Brain Attend and Decode (BAnD) BAnD uses residual convolutional neural networks for spatial feature extraction and self-attention mechanisms temporal modeling. We achieve significant performance gain compared to previous works on a 7-task benchmark from the Human Connectome Project-Young Adult dataset.
  arXiv  Detail & Related papers  (2020-04-10T21:29:34Z)
• A Hybrid 3DCNN and 3DC-LSTM based model for 4D Spatio-temporal fMRI data: An ABIDE Autism Classification study [0.0]
  We introduce an end-to-end algorithm capable of extracting features from full 4-D data using 3-D CNNs and 3-D Magnetical LSTMs. Our results show that the proposed model achieves state of the art results on single sites with F1-scores of 0.78 and 0.7 on NYU and UM sites, respectively.
  arXiv  Detail & Related papers  (2020-02-14T11:52:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.