Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Statistics and AI - A Fireside Conversation.

Harvard data science review·2026

Same author

Cardiovascular-Kidney-Metabolic Syndrome: Conceptualising an Approach to Health Economic Modelling.

Diabetes, obesity & metabolism·2026

Same author

Artificial Intelligence in Image-Based Cardiovascular Disease Analysis.

Annual review of biomedical data science·2026

Same author

Multi-organ imaging and genetics show the impact of sleep patterns on the human brain and body.

Communications medicine·2026

Same author

Scalable subclonal reconstruction of cancer cells in DNA sequencing data using a penalized likelihood model.

bioRxiv : the preprint server for biology·2026

Same author

Connectome-based spatial statistics enabling large-scale population analyses of human connectome across cohorts.

bioRxiv : the preprint server for biology·2026

Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026

Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026

Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 5, 2025

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

Self-supervised graph contrastive learning with diffusion augmentation for functional MRI analysis and brain disorder

Xiaochuan Wang¹, Yuqi Fang¹, Qianqian Wang¹

¹Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.

Medical Image Analysis

|December 5, 2024

Summary

This summary is machine-generated.

This study introduces GCDA, a novel self-supervised learning framework for analyzing brain activity using resting-state functional MRI (rs-fMRI). GCDA enhances graph contrastive learning by preserving original blood-oxygen-level-dependent signals for more accurate automated brain disorder analysis.

Keywords:

Contrastive learning Data augmentation Diffusion model Functional MRI

More Related Videos

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Jun 5, 2025

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Area of Science:

Neuroimaging
Machine Learning
Computational Neuroscience

Background:

Resting-state functional magnetic resonance imaging (rs-fMRI) is crucial for non-invasive brain activity study and automated disorder analysis.
Current fMRI learning methods heavily depend on labeled data, which is time-consuming and resource-intensive to acquire.
Graph contrastive learning offers a potential solution for limited labeled data but existing augmentation may harm blood-oxygen-level-dependent (BOLD) signals.

Purpose of the Study:

To propose a self-supervised graph contrastive learning framework with diffusion augmentation (GCDA) for functional MRI analysis.
To address the issue of data augmentation damaging original BOLD signals in fMRI analysis.
To develop a method that reduces reliance on labeled data for brain disorder analysis.

Main Methods:

Developed a GCDA framework comprising a pretext and a task-specific model.
Implemented a graph diffusion augmentation (GDA) module to perturb graph edges and nodes while preserving BOLD signal integrity.
Utilized two graph isomorphism networks for feature extraction in a self-supervised contrastive learning manner within the pretext model.

Main Results:

The proposed GCDA framework effectively analyzes functional MRI data without requiring labeled training data.
The GDA module successfully preserves the integrity of original BOLD signals during augmentation.
Experiments on two rs-fMRI cohorts (1230 subjects) showed superior performance compared to state-of-the-art methods.

Conclusions:

GCDA offers an effective self-supervised approach for functional MRI analysis, overcoming limitations of traditional methods.
The diffusion augmentation strategy preserves crucial BOLD signal information, enhancing feature extraction.
This framework holds promise for advancing automated brain disorder analysis with limited labeled data.