EUVIMEDOpdag EUVIMED
Crossref

Spatiotemporal coarse‐to‐fine diffusion model for automatic brain network generation

Qiankun Zuo, Jiaojiao Yu, Conghuan Ye, Ling Chen, Hao Tian, Yixian Wu, Yudong Zhang

Medical Physics · 2025

DOI: 10.1002/mp.17833 ↗

At a glance

Journal article in Medical Physics, 2025. Written by Qiankun Zuo and 6 co-authors. Institution: Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan, Hubei, China. Major MEDLINE topics: Brain, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Cited 1 times so far (Crossref); 54 references. Funded by: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province, Education Department Scientific Research Program Project of Hubei Province of China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Functional magnetic resonance imaging (fMRI) has emerged as a transformative tool in analyzing and understanding brain diseases. It is a challenge to learn effective features from the high‐dimensional fMRI. Most studies have focused on extracting connectivity‐based features for disease analysis. However, they heavily rely on the software toolboxes to construct connectivity‐based features, which may suffer from large errors because of different manual parameter settings and thus lead to bad performance in brain disorder analysis.

Purpose

A novel brain denoiser model is proposed to transform four‐dimensional fMRI (4D fMRI) into a brain network in a unified framework for brain disease analysis.

Methods

By introducing anatomical knowledge, the proposed model first reduces the 4D fMRI into a 2D coarse region‐of‐interest(ROI)‐based time series and then diffuses it into noisy status by gradually adding Gaussian noise. Moreover, the coarse‐to‐fine transformer refinement is designed to capture multi‐scale temporal dynamics and iteratively remove unrelated multi‐frequency noise. Besides, the low‐frequency preservation module is devised to enhance the effective signal at low frequencies during the denoising process. This can improve the signal‐to‐noise ratio at each timestep, which ensures accurate restoration of ROI time series and improves the performance of brain network construction.

Results

We evaluate the performance of the Brain Denoiser on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and the Autism Brain Imaging Data Exchange (ABIDE) dataset, demonstrating its ability to effectively suppress noise while preserving the underlying neural signals. Comparative analyses with related competing methods demonstrate the superiority of the proposed model.

Conclusions

Generally, the proposed model presents a robust and innovative solution for brain network generation, paving the way for efficient analysis of brain disease.

Subjects

MeSH terms (MEDLINE)

BrainMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansAutomationDiffusionSignal-To-Noise RatioAlzheimer Disease

Author keywords

brain imagingbrain networkcoarse‐to‐fine diffusion model

Authors and institutions

  • Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan, Hubei, China.
  • School of Information Engineering, Hubei University of Economics, Wuhan, Hubei, China.
  • Hubei Internet Finance Information Engineering Technology Research Center, Hubei University of Economics, Wuhan, Hubei, China.
  • School of Information Management, Institute of Big Data and Digital Economy, Hubei University of Economics, Wuhan, Hubei, China.
  • School of Mechanical Engineering, Beijing Institute of Petrochemical Technology, Beijing, China.
  • School of Computing and Mathematic Sciences, University of Leicester, Leicester, UK.

Funding

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hubei Province
  • Education Department Scientific Research Program Project of Hubei Province of China

Cite

APA

Zuo, Q., Yu, J., Ye, C., Chen, L., Tian, H., Wu, Y., & Zhang, Y. (2025). Spatiotemporal coarse‐to‐fine diffusion model for automatic brain network generation. Medical Physics. https://doi.org/10.1002/mp.17833

Vancouver

Zuo Q, Yu J, Ye C, Chen L, Tian H, Wu Y, et al. Spatiotemporal coarse‐to‐fine diffusion model for automatic brain network generation. Medical Physics. 2025. doi:10.1002/mp.17833

BibTeX
@article{Zuo2025,
  author = {Zuo, Qiankun and Yu, Jiaojiao and Ye, Conghuan and Chen, Ling and Tian, Hao and Wu, Yixian and Zhang, Yudong},
  title = {Spatiotemporal coarse‐to‐fine diffusion model for automatic brain network generation},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17833}
}
Start for free →