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

Harmonized psychiatric diagnosis data from the Adolescent Brain Cognitive Development Study.

Research square·2026

Same author

Operationalizing the Whole of Psychic Life: Toward a Structured Framework for Psychopathology.

Psychopathology·2026

Same author

Guidelines for the prevention of psychosis from the World Federation of Societies of Biological Psychiatry (WFSBP) and EPI Canada.

The world journal of biological psychiatry : the official journal of the World Federation of Societies of Biological Psychiatry·2026

Same author

Brain age prediction in generalized anxiety disorder using a convolutional neural network.

Translational psychiatry·2026

Same author

Recovery Processes Reported by People with Severe Mental Illness in Brazil: Systematic Review and Thematic Synthesis.

Transcultural psychiatry·2026

Same author

Real-world comprehensive care of people living with schizophrenia: recommendations across different settings and clinical stages.

World psychiatry : official journal of the World Psychiatric Association (WPA)·2026

Search research articles

Related Experiment Video

Updated: Mar 10, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia.

Walter H L Pinaya¹, Ary Gadelha², Orla M Doyle³

¹Center of Mathematics, Computation, and Cognition. Universidade Federal do ABC, Santo André, Brazil.

Scientific Reports

|December 13, 2016

Summary

This summary is machine-generated.

Deep learning models like deep belief networks (DBN) show promise in identifying brain differences in schizophrenia patients using structural MRI scans. However, DBNs struggled to classify first-episode psychosis patients, suggesting limitations in current deep learning approaches for psychiatric disorders.

More Related Videos

Brain Morphology of Cannabis Users With or Without Psychosis: A Pilot MRI Study

Brain Morphology of Cannabis Users With or Without Psychosis: A Pilot MRI Study

Published on: August 18, 2020

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: Mar 10, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Brain Morphology of Cannabis Users With or Without Psychosis: A Pilot MRI Study

Brain Morphology of Cannabis Users With or Without Psychosis: A Pilot MRI Study

Published on: August 18, 2020

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
Psychiatry
Machine Learning

Background:

Neuroimaging studies reveal schizophrenia's complex pathophysiology but face challenges due to patient heterogeneity.
Variability in neuroimaging results highlights the need for advanced analytical methods to identify consistent patterns.

Purpose of the Study:

To apply a deep learning model, specifically a deep belief network (DBN), to structural MRI data for improved schizophrenia diagnosis.
To investigate the DBN's efficacy in differentiating between healthy controls and individuals with schizophrenia and first-episode psychosis.

Main Methods:

Structural MRI data from 83 healthy controls and 143 schizophrenia patients were analyzed using a deep belief network (DBN).
The DBN was trained to extract features from brain morphometry data, and its classification performance was compared to a support vector machine (SVM).
Performance was also evaluated for classifying 32 first-episode psychosis patients.

Main Results:

The DBN identified significant morphometric differences between schizophrenia patients and healthy controls in frontal, temporal, parietal, and insular cortices, as well as subcortical regions.
The DBN achieved a higher classification accuracy (73.6%) compared to the SVM (68.1%).
The DBN exhibited a 56.3% error rate in classifying first-episode psychosis patients, indicating that learned representations were not generalizable to this group.

Conclusions:

Deep learning, particularly DBNs, offers a powerful tool for analyzing neuroimaging data and enhancing the understanding of schizophrenia's underlying brain characteristics.
Current deep learning models trained on chronic schizophrenia patients may not be directly applicable to early stages of the disorder, such as first-episode psychosis.
Further research is needed to refine deep learning approaches for improved diagnostic accuracy and understanding of psychiatric disorders across different stages.