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 authorSame journal

Magnetically Compatible and Fiberless fNIRS Enables Simultaneous Multimodal Imaging with Optically Pumped Magnetometer MEG.

NeuroImage·2026
Same author

A spatiotemporal dependency-aware lightweight CNN-ViT network for 3D MRF with a balanced acceleration strategy.

Medical image analysis·2026
Same author

Stabilizing and cleaning functional connectivity measures via native eigenspace denoising of resting state fMRI data.

NeuroImage·2026
Same author

AmygdalaGo-BOLT for boundary-aware segmentation of the human amygdala.

Cell reports methods·2026
Same author

Laminar fMRI using magnetization transfer contrast at 7 T.

NeuroImage·2026
Same author

Normative T<sub>1</sub> and T<sub>2</sub> Brain Atlases Across the Adult Lifespan in a Chinese Cohort: Multicenter Quantitative MRI Benchmarks for Ageing and Neurodegenerative Research.

Human brain mapping·2026

Related Experiment Video

Updated: Sep 23, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.2K

A deep learning-based multisite neuroimage harmonization framework established with a traveling-subject dataset.

Dezheng Tian1, Zilong Zeng1, Xiaoyi Sun2

  • 1State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China; Beijing Key Laboratory of Brain Imaging and Connectomics, Beijing Normal University, Beijing 100875, China; IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing 100875, China.

Neuroimage
|May 14, 2022
PubMed
Summary

A new deep learning framework effectively harmonizes multisite MRI data by disentangling site effects and brain features. This improves reliability and reproducibility in large-scale brain imaging studies.

Keywords:
Big dataConvolutional networkGray matterMachine learningMulticenterSite effect

More Related Videos

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States
06:25

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Published on: January 19, 2024

1.1K
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

15.8K

Related Experiment Videos

Last Updated: Sep 23, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.2K
Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States
06:25

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Published on: January 19, 2024

1.1K
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

15.8K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Brain Science

Background:

  • Multisite MRI datasets are crucial for understanding brain function and disorders.
  • Site effects in neuroimaging data hinder consistent findings across studies.
  • Harmonization methods are vital for reliable multisite neuroimaging research.

Purpose of the Study:

  • To develop a deep learning framework for harmonizing multisite neuroimaging data.
  • To effectively eliminate site effects while preserving biological information.
  • To enhance the reliability and reproducibility of multisite brain studies.

Main Methods:

  • A deep learning framework was proposed to disentangle site factors and brain features.
  • The framework was trained on a traveling subject dataset (SRPBS).
  • Gray matter volume maps from eight sites were harmonized to a target site.

Main Results:

  • The framework significantly reduced intersite differences in gray matter volumes.
  • Encoders successfully captured both site-specific and brain-specific features.
  • The method outperformed conventional statistical harmonization techniques.

Conclusions:

  • The proposed deep learning framework offers a powerful and interpretable solution for harmonizing multisite neuroimaging data.
  • This approach enhances data reliability and reproducibility in brain development and disorder research.
  • The framework allows for expandable integration of new sites without full retraining.