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

Tree Imagery in Drawing Tests for Screening Mental Disorders: A Systematic Review and Meta-Analysis.

Depression and anxiety·2026

Same author

Extreme heat and mental health: systematic review and qualitative investigation of risk and protective factors.

Psychological medicine·2026

Same author

Stressful life events and their association with symptom severity and functioning in first-episode psychosis.

Schizophrenia (Heidelberg, Germany)·2026

Same author

Co-expression-based models improve eQTL predictions for transcriptome-wide association studies and highlight new schizophrenia-associated genes.

Nature genetics·2026

Same author

Variations of structural-functional coupling in post-traumatic stress disorder are associated with underlying molecular and transcriptional features.

Psychological medicine·2026

Same author

Characterizing insula functional connectivity alterations in obsessive-compulsive disorder: from parcellation and gradient models.

Cerebral cortex (New York, N.Y. : 1991)·2026

Search research articles

Related Experiment Video

Updated: Sep 23, 2025

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 2014

Graph Convolutional Networks Reveal Network-Level Functional Dysconnectivity in Schizophrenia.

Du Lei^1,2,3, Kun Qin^1,3, Walter H L Pinaya⁴

¹Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital, Sichuan University, Chengdu, China.

Schizophrenia Bulletin

|May 15, 2022

Summary

Graph convolutional networks (GCN) accurately classify schizophrenia by analyzing brain connectivity. This method highlights striatal area deficits linked to negative symptoms, offering a promising diagnostic tool.

Keywords:

connectome graph analysis machine learning magnetic resonance imaging neuroimaging psychosis

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

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: Sep 23, 2025

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 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

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:

Neuroscience
Computational Psychiatry
Medical Imaging Analysis

Background:

Schizophrenia is increasingly viewed as a disorder of brain dysconnectivity.
Graph convolutional networks (GCN) analyze complex relationships within brain networks using imaging features.
GCNs explore pairwise similarities in brain region imaging features to reveal network abnormalities.

Purpose of the Study:

To investigate topological abnormalities in functional brain networks of individuals with schizophrenia using GCN.
To compare the classification performance of GCN against support vector machine (SVM).
To identify salient brain regions and their topological properties associated with schizophrenia and symptom severity.

Main Methods:

Utilized resting-state functional magnetic resonance imaging (fMRI) data from 505 schizophrenia patients and 907 controls.
Extracted whole-brain functional connectivity matrices for each participant.
Applied GCN and SVM for classification, analyzed saliency maps, and correlated nodal properties with symptom severity.

Main Results:

GCN achieved a classification accuracy of 85.8%, outperforming SVM's 80.9%.
Discriminative brain regions included striatal areas (putamen, pallidum, caudate) and the amygdala.
Post hoc analysis revealed significant differences in nodal efficiency of the putamen and pallidum, correlating with negative symptoms.

Conclusions:

GCN demonstrates high accuracy in classifying schizophrenia at the individual level, suggesting its potential as a diagnostic tool.
Functional topological deficits in striatal areas may be a key neural correlate of negative symptomatology in schizophrenia.