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

The exposome of brain aging across 34 countries.

Nature medicine·2026

Same author

Cognition, but not affect, rests upon a segregated intrinsic network architecture.

bioRxiv : the preprint server for biology·2026

Same author

Effects of alcohol misuse on the evolution of anxiety during the COVID-19 pandemic in France: results from CONFINS cohort.

BMJ open·2026

Same author

Effectiveness of antihypertensive drugs for secondary prevention of ischaemic stroke: a nationwide historic cohort study.

BMJ open·2025

Same author

Proteogenomics in cerebrospinal fluid and plasma reveals new biological fingerprint of cerebral small vessel disease.

Nature aging·2025

Same author

GINNA, a 33 resting-state networks atlas with meta-analytic decoding-based cognitive characterization.

Communications biology·2025

Search research articles

Related Experiment Video

Updated: Nov 18, 2025

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

Deep Learning-based Classification of Resting-state fMRI Independent-component Analysis.

Victor Nozais^1,2,3,4, Philippe Boutinaud^1,5, Violaine Verrecchia^1,2,3,4

¹Ginesislab, Bordeaux, France.

Neuroinformatics

|February 5, 2021

Summary

This study introduces a deep learning method to automatically classify brain resting-state networks (RSNs) from fMRI data. The approach achieved 92% accuracy, enabling new ways to analyze brain connectivity and create RSN atlases.

Keywords:

Artificial intelligence Brain functional network Classification.Independent‐component analysis Neuroimaging cohort Resting‐state

More Related Videos

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

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

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

Published on: August 5, 2014

Related Experiment Videos

Last Updated: Nov 18, 2025

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

A Method for Investigating Age-related Differences in the Functional Connectivity of Cognitive Control Networks Associated with Dimensional Change Card Sort Performance

Published on: May 7, 2014

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

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

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

Published on: August 5, 2014

Area of Science:

Neuroscience
Computational Neuroscience
Machine Learning

Background:

Resting-state fMRI (fMRI) reveals spatially organized resting-state networks (RSNs) of functionally connected brain regions.
Analyzing inter-RSN connectivity offers a valuable spatial scale for understanding functional connectome variability.

Purpose of the Study:

To develop a deep learning approach for automated classification of independent components (ICs) into predefined RSNs.
To enable robust, individual-level analysis and comparison of functional connectomes across datasets.

Main Methods:

A multilayer perceptron (MLP) was trained to classify ICs into 45 RSNs using the BIL&GIN dataset (282 participants for training).
Hyperparameter optimization was performed using a 5-dimensional parameter grid search.
The model achieved 92% accuracy on independent data, with good spatial overlap for cortical RSNs.

Main Results:

An RSN atlas was created from the MRi-Share dataset, defining 29 RSNs covering 96% of gray matter.
An individual-based analysis revealed subdivisions within the default-mode network into 4 distinct networks.
Minimal overlap was observed between RSNs, except in specific regions like the angular gyrus and precuneus.

Conclusions:

The developed deep learning classifier automates RSN identification from fMRI data.
This tool facilitates the analysis of individual datasets and statistical comparisons between different studies.
The study provides a valuable resource for the neuroscience community to advance RSN research.