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

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Visible-Light-Induced Hydroxyperfluoroalkylation of Alkenes to Access β-Perfluoroalkyl Alcohols.

Chemistry, an Asian journal·2026

Same author

Association of the CHG index combined with obesity indices and incident cardiometabolic multimorbidity in a nationwide prospective cohort study.

Scientific reports·2026

Same author

Mechanochemical Piezoelectric Catalysis: Advancing the Hydrogenation of Alkenes.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

A longitudinal study on the intergenerational transmission mechanism of music preference on adolescents' emotion regulation.

Acta psychologica·2026

Same author

RNA demethylase CsALKBH8 enhances postharvest disease resistance of citrus fruit against penicillium digitatum via m<sup>6</sup>A-mediated transcript regulation.

Food research international (Ottawa, Ont.)·2026

Same author

Molecular taxonomy and spatial organization define neuronal subtypes in the mouse inferior colliculus.

iScience·2026

Search research articles

Related Experiment Video

Updated: Sep 21, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization.

Mengting Liu¹, Piyush Maiti¹, Sophia Thomopoulos¹

¹USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

|June 1, 2022

Summary

This summary is machine-generated.

This study introduces a novel deep learning approach for harmonizing brain MRI scans from different scanners without needing site labels. This method effectively removes cross-site variability, enabling better data pooling for large-scale research.

Keywords:

GAN MRI Harmonization Style Encoding

More Related Videos

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Related Experiment Videos

Last Updated: Sep 21, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Area of Science:

Neuroimaging
Medical Image Analysis
Artificial Intelligence

Background:

Large-scale neuroimaging studies require pooling MRI data from multiple scanners and protocols.
Retrospective harmonization is crucial for analyzing existing, uncoordinated datasets.
Current methods struggle to differentiate image variability from population variability.

Purpose of the Study:

To develop a novel unsupervised method for retrospective harmonization of multi-site MRI data.
To treat cross-site MRI harmonization as a style transfer problem.
To eliminate the need for traveling subjects or demographic matching in harmonization.

Main Methods:

Utilized a fully unsupervised deep learning framework based on a Generative Adversarial Network (GAN).
Framed MRI harmonization as a style transfer problem, encoding style information from reference images.
Trained the model on diverse data from five large-scale multi-site datasets.

Main Results:

Successfully harmonized MR images and matched intensity profiles across different sites and scanners without prior site labels.
Demonstrated effectiveness without relying on traveling subjects or controlling for clinical/demographic information.
Showed successful harmonization of images from unseen scanners and protocols when diverse training data was used.

Conclusions:

The proposed style-encoding GAN offers a powerful tool for retrospective MRI harmonization.
This method facilitates data pooling for large-scale collaborative neuroimaging research.
It overcomes limitations of existing methods by treating harmonization as style transfer.