Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

USP20-mediated PGAM1 stabilization promotes glycolysis and confers osimertinib resistance in non-small cell lung carcinoma.

Oncogene·2026
Same author

Atomic-level protein-ligand recognition with PBCNet2.0 for probe discovery.

Nature chemical biology·2026
Same author

A dual-layer vector map encryption scheme using 4D hyperchaos and SM4.

Scientific reports·2026
Same author

Neural Wave Propagation for Surgical Video Action Recognition: A New Dataset and Baseline.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

The relationship between background parenchymal enhancement, amount of fibroglandular tissue and synchronous contralateral breast cancer in preoperative magnetic resonance imaging of newly diagnosed breast cancer patients.

BMC medical imaging·2026
Same author

Discovery of Novel Alkynylbenzene Scaffold-Based PTPN2-Selective Degrader PD-305 with Exceptional Potency and In Vivo Efficacy.

Journal of medicinal chemistry·2026

Related Experiment Video

Updated: Jun 5, 2025

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.0K

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis.

Wenyang Li1, Mingliang Wang1, Mingxia Liu2

  • 1School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 6, 2024
PubMed
Summary

This study introduces a novel framework for analyzing brain functional connectivity (FC) from resting-state fMRI data across multiple sites. The method learns invariant representations for improved brain disorder diagnosis.

Keywords:
Disentangled representationFunctional connectivityMulti-site dataRiemannian manifold

More Related Videos

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

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

Published on: November 8, 2012

26.2K

Related Experiment Videos

Last Updated: Jun 5, 2025

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.0K
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

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

Published on: November 8, 2012

26.2K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Computational Neuroscience

Background:

  • Functional connectivity (FC) derived from resting-state fMRI is crucial for understanding brain disorders.
  • Existing FC analysis methods often overlook Riemannian manifold geometry and struggle with multi-site data limitations.

Purpose of the Study:

  • To propose a novel Riemannian Manifold-based Disentangled Representation Learning (RM-DRL) framework.
  • To learn invariant representations from multi-site fMRI data for robust brain disorder diagnosis.

Main Methods:

  • Developed an SPD-based encoder to preserve Riemannian geometry of FC matrices.
  • Implemented a disentangled representation module to separate domain-specific and invariant features.
  • Utilized a decoder and four training objectives to enhance disentanglement learning.

Main Results:

  • The RM-DRL framework effectively learns unified representations from multi-site fMRI data.
  • The method achieved superior performance in brain disorder diagnosis compared to state-of-the-art approaches.
  • Demonstrated the importance of exploring Riemannian manifold properties in FC analysis.

Conclusions:

  • The proposed RM-DRL framework offers a powerful approach for multi-site fMRI data analysis in brain disorder research.
  • Integrating Riemannian geometry and disentangled representation learning enhances model robustness and diagnostic accuracy.
  • This work paves the way for more effective machine learning applications in neuroimaging.