Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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 Evolving Landscape of Terahertz Biosensing: From Sensitivity to Precision.

ACS applied materials & interfaces·2026
Same author

SSGJ-608 in moderate-to-severe plaque psoriasis: a multicenter, randomized, open-label, phase 3 study.

Frontiers in immunology·2026
Same author

Nanocrystal-tailored recombination for all-perovskite tandem solar modules.

Nature·2026
Same author

SPARC promotes angiogenesis and cell migration via VEGFR2-ERK1/2-SPHK1 axis in pterygium.

Experimental eye research·2026
Same author

Effects of High Temperature on Development, Survival, and Antioxidant Responses of Immature <i>Monolepta hieroglyphica</i>.

Insects·2026
Same author

Shared genetic architecture between the topology of brain white matter structural connectome and fluid intelligence.

Communications biology·2026

Related Experiment Video

Updated: Mar 23, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K

An Efficient Contrastive Deep Learning Model for Identifying Schizophrenia-Specific Neuroanatomical Variations.

Lin Du1,2, Biying Peng1,2, Yuqing Sun1,2

  • 1State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China.

Schizophrenia Bulletin
|March 21, 2026
PubMed
Summary
This summary is machine-generated.

Researchers developed DECODE-SZ to identify schizophrenia-specific brain changes. These specific neuroanatomical alterations strongly correlate with clinical symptoms, offering potential biomarkers for schizophrenia heterogeneity.

Keywords:
contrastive learningdeep learningneuroanatomyschizophrenia

More Related Videos

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.7K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

4.8K

Related Experiment Videos

Last Updated: Mar 23, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.5K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.7K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

4.8K

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Psychiatry

Background:

  • Schizophrenia (SZ) presents with diverse clinical symptoms and brain structural differences, but links between specific abnormalities and symptoms are unclear.
  • Identifying SZ-specific neuroanatomical variations may improve understanding of pathophysiology and reveal biomarkers for clinical heterogeneity.

Purpose of the Study:

  • To develop a novel model, DECODE-SZ, for isolating schizophrenia-specific neuroanatomical features from structural MRI data.
  • To investigate the association between these specific features and clinical symptoms (PANSS scores) in schizophrenia patients.

Main Methods:

  • DECODE-SZ integrates contrastive learning, 3D CNNs, and VAEs to extract SZ-specific gray matter features.
  • Applied to MRI data from 641 SZ patients and 609 controls across 8 sites, using leave-one-site-out cross-validation.
  • Analyzed relationships between SZ-specific features, PANSS scores, and demographic variables.

Main Results:

  • DECODE-SZ successfully extracted SZ-specific gray matter features.
  • These features showed stronger associations with PANSS scores compared to common variations.
  • Consistent alterations were found across sites, and DECODE-SZ outperformed traditional VAEs.

Conclusions:

  • SZ-specific neuroanatomical alterations show potential as biomarkers for clinical outcomes in schizophrenia.
  • DECODE-SZ is a promising tool for advancing schizophrenia research and informing diagnostic/therapeutic strategies.