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

Search research articles

Related Experiment Video

Updated: Feb 19, 2026

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

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

Regina J Meszlényi^1,2, Krisztian Buza^2,3, Zoltán Vidnyánszky^1,2

¹Department of Cognitive Science, Budapest University of Technology and Economics, Budapest, Hungary.

Frontiers in Neuroinformatics

|November 2, 2017

Summary

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

Daily Predictors of Psychotic-Like Experiences in Older Adults: The Role of Sleep Quality, Negative Emotions, and Cognitive Failures.

Journal of sleep research·2026

Same author

Regional brain aging patterns reveal disease-specific pathways of neurodegeneration.

medRxiv : the preprint server for health sciences·2025

Same author

Deep learning approach for automatic assessment of schizophrenia and bipolar disorder in patients using R-R intervals.

PLoS computational biology·2025

Same author

Reward boosts cognitive control during working memory maintenance.

Scientific reports·2025

Same author

A large-scale multi-centre study characterising atrophy heterogeneity in Alzheimer's disease.

NeuroImage·2025

Same author

Assessing the association between ADHD and brain maturation in late childhood and emotion regulation in early adolescence.

Translational psychiatry·2025

We introduce a novel connectome-convolutional neural network (CCNN) for brain network classification using resting state fMRI data. Our CCNN model effectively distinguishes between subject groups and integrates multiple connectivity metrics for improved performance.

Area of Science:

Neuroscience
Machine Learning
Medical Imaging

Background:

Machine learning is increasingly used for resting state fMRI network-based classification.
Convolutional neural networks (CNNs) are a recent and underexplored approach in this domain.

Purpose of the Study:

To introduce a novel convolutional neural network architecture, the connectome-convolutional neural network (CCNN), for functional connectome classification.
To evaluate the CCNN's ability to distinguish between subject groups using simulated and real-world datasets.

Main Methods:

Developed a connectome-convolutional neural network (CCNN) architecture tailored for brain connectome data.
Tested the CCNN on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification.

Keywords:

Dynamic Time Warping classification connectome convolutional neural network functional magnetic resonance imaging resting state connectivity

More Related Videos

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

Related Experiment Videos

Last Updated: Feb 19, 2026

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

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

Investigated the model's capability to integrate diverse functional connectivity metrics.

Main Results:

The CCNN model demonstrated efficient discrimination between subject groups in both simulated and real datasets.
The CCNN successfully combined information from various functional connectivity metrics.
Models utilizing a combination of connectivity descriptors outperformed those using a single metric.

Conclusions:

The proposed CCNN is a flexible and effective tool for functional connectome classification tasks.
The CCNN can be readily adapted for various classification or regression problems by adjusting connectivity descriptor combinations.
This approach advances the application of deep learning in neuroimaging analysis.