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

Multiparametric Characterization of Tough Clots Following Stroke Thrombectomy.

Clinical neuroradiology·2026

Same author

Towards a more inclusive psychiatry: diversity among presenters and participants in the 25th World Congress of Psychiatry.

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

Same author

Sine spin flat-detector CT for enhanced brain parenchyma visualization: an intraindividual comparison on a latest-generation angiography system.

Neuroradiology·2026

Same author

High-resolution ultrasound vs. MR neurography in upper extremity neuropathies: exploratory analysis of perceived additional diagnostic value in routine clinical practice.

European radiology·2026

Same author

Structure-based design of pyrazole derivatives targeting the human Cyclophilin D binding site.

International journal of biological macromolecules·2026

Same author

MR Neurography in Children and Adolescents: Multiparametric Assessment of Peripheral Nerve Involvement in Long-chain Fatty Acid Oxidation Disorders.

Investigative radiology·2026

Search research articles

Related Experiment Video

Updated: Sep 21, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Structural MRI-Based Schizophrenia Classification Using Autoencoders and 3D Convolutional Neural Networks in

Roman Vyškovský¹, Daniel Schwarz¹, Vendula Churová¹

¹Faculty of Medicine, Institute of Biostatistics and Analyses, Masaryk University, Kamenice 3, 625 00 Brno, Czech Republic.

|May 28, 2022

Summary

This summary is machine-generated.

Machine learning models, including stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN), were trained to classify schizophrenia using MRI data. Stacked autoencoders demonstrated superior performance, especially with voxel-based morphometry preprocessing.

Keywords:

3D CNN autoencoders classification deep learning deformation-based morphometry schizophrenia voxel-based morphometry

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: Sep 21, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Area of Science:

Neuroscience
Artificial Intelligence
Medical Imaging

Background:

Schizophrenia diagnosis lacks objective tools, relying heavily on clinical assessment.
Advancements in computational power and machine learning offer new diagnostic avenues.
Structural magnetic resonance imaging (sMRI) provides detailed brain structure information.

Purpose of the Study:

To evaluate the effectiveness of deep learning models for schizophrenia classification using sMRI data.
To compare the performance of stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN).
To investigate the impact of complex feature extraction methods on classifier accuracy.

Main Methods:

Utilized sMRI data from 52 schizophrenia patients and 52 healthy controls.
Employed stacked autoencoders (SAE) and 3D convolutional neural networks (3D CNN) for classification.
Compared preprocessing techniques: voxel-based morphometry (VBM), deformation-based morphometry (DBM), and spatial normalization.

Main Results:

The most successful model, SAE, achieved an average accuracy of 69.62% (sensitivity 68.85%, specificity 70.38%).
SAE outperformed 3D CNN in classifying schizophrenia.
Voxel-based morphometry preprocessing significantly improved SAE performance.

Conclusions:

Stacked autoencoders show promise for objective schizophrenia classification using sMRI.
Feature extraction methods, particularly VBM, enhance deep learning model accuracy.
Further research into advanced machine learning for neuropsychiatric disorders is warranted.