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

Cerebellar volume alterations are associated with cognitive dysfunction and fatigue in patients with systemic lupus erythematosus.

BMC rheumatology·2026
Same author

Preclinical feasibility and validation of MRI thermometry dedicated to interstitial photodynamic therapy of glioblastoma.

Photodiagnosis and photodynamic therapy·2026
Same author

Diagnostic value of non-contrast MRI sequences in the emergency evaluation of acute isolated headache.

Journal of neuroradiology = Journal de neuroradiologie·2026
Same author

Cultural bias in large language models' ability to follow neuroradiology guidelines.

European radiology·2026
Same author

Toward better capture of microstructural damage in stroke using advanced diffusion-weighted imaging parameters.

Diagnostic and interventional imaging·2026
Same author

Multi-level language deficits in behavioural frontotemporal degeneration and related disorders.

Brain communications·2026

Related Experiment Video

Updated: Jul 3, 2026

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
11:03

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

NeuroHarm‑Kit: An open‑source toolbox for benchmarking deep‑learning harmonization of multi‑site T1‑weighted MRI.

Barnabé Hache1, Vincent Roca2, Grégory Kuchcinski3

  • 1Univ. Lille, Inserm, CHU Lille, U1172 - LilNCog - Lille Neuroscience & Cognition, Lille, F-59000, France.

Neuroimage
|July 1, 2026
PubMed
Summary
This summary is machine-generated.

NeuroHarm-Kit is a new open-source toolbox for harmonizing multi-site magnetic resonance imaging (MRI) data. It allows researchers to compare different deep learning models for brain scan harmonization, improving data consistency.

Keywords:
BenchmarkBrain MRIDeep learningHarmonizationMultisiteToolbox

More Related Videos

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Jul 3, 2026

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
11:03

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Medical Image Analysis

Background:

  • Multi-site magnetic resonance imaging (MRI) studies are crucial for understanding brain structure across diverse populations.
  • Scanner-related variability poses a significant challenge, hindering the integration and analysis of data from different sites.
  • Existing harmonization methods often lack standardization and direct comparison frameworks.

Purpose of the Study:

  • To introduce NeuroHarm-Kit, an open-source, end-to-end toolbox for harmonizing 3D T1-weighted MRI scans.
  • To provide a standardized framework for reproducible, head-to-head comparisons of state-of-the-art deep learning harmonization models.
  • To enable researchers to select the most appropriate harmonization strategy based on specific research objectives and data characteristics.

Main Methods:

  • NeuroHarm-Kit integrates multiple deep learning harmonization models: STGAN, HACA3, MURD, DISARM++, and IGUANe.
  • The toolbox offers standardized preprocessing pipelines and pretrained model weights for ease of use.
  • Performance evaluation was conducted on traveling-subject and healthy aging cohorts, assessing metrics like intensity-distribution alignment, anatomical fidelity, and biological information preservation.

Main Results:

  • Different deep learning harmonization methods exhibit varying strengths, excelling in distinct metrics.
  • No single method uniformly outperforms across all evaluated criteria, highlighting the need for tailored harmonization approaches.
  • NeuroHarm-Kit successfully demonstrated the comparative performance of these models on real-world neuroimaging datasets.

Conclusions:

  • The choice of harmonization method should be guided by specific research goals and data properties.
  • NeuroHarm-Kit provides a valuable, ready-to-use framework for researchers to compare and select optimal harmonization strategies.
  • This toolbox aims to enhance reproducibility and accelerate innovation in multi-site neuroimaging harmonization by lowering methodological barriers.