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

What Does Infant Participation Look like? An International Delphi Study of Maternal Caregivers and Health Professionals.

Physical & occupational therapy in pediatrics·2026

Same author

Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation.

IEEE transactions on medical imaging·2026

Same author

Acceptability of telehealth-delivered Alberta Infant Motor Scale for Australian parents: A mixed-methods analysis.

Developmental medicine and child neurology·2026

Same author

The Effect of Preterm Birth on Physical Activity for 9- to 12-Year-Old Children.

The Journal of pediatrics·2026

Same author

Relationships between cerebral blood flow and cognition in young adults born very preterm and at term.

Scientific reports·2026

Same author

Associations Between the Alberta Infant Motor Scale and Motor and Gait Outcomes at 4-5 Years in Children Born Very Preterm: A Prospective Cohort Study.

Physical & occupational therapy in pediatrics·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 29, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Harmonizing flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization.

Farzad Beizaee¹, Gregory A Lodygensky², Chris L Adamson³

¹LIVIA, ÉTS, Montreal, Quebec, Canada; ILLS , McGill - ETS - Mila - CNRS - Université Paris-Saclay - CentraleSupelec, Canada; CHU Sainte-Justine, University of Montreal, Montreal, Canada.

Medical Image Analysis

|February 7, 2025

Summary

This summary is machine-generated.

This study introduces an unsupervised framework using normalizing flows to harmonize magnetic resonance (MR) images, improving deep learning model generalization across different sites and devices. The method effectively aligns MR images without source data, enhancing segmentation and age estimation tasks.

Keywords:

Brain MRI MRI harmonization Normalizing flows Test-time adaptation

More Related Videos

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

Related Experiment Videos

Last Updated: May 29, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

Area of Science:

Medical Imaging
Artificial Intelligence
Neuroscience

Background:

Magnetic Resonance (MR) image acquisition exhibits heterogeneity due to lack of standardization and varying parameters across sites and devices.
This image heterogeneity negatively impacts the generalization capabilities of deep neural networks (DNNs) in medical image analysis.
Existing harmonization methods often require source domain data or are task-specific, limiting their applicability.

Purpose of the Study:

To propose a novel unsupervised and source-free harmonization framework for magnetic resonance (MR) images.
To align heterogeneous MR images to a common distribution, thereby enhancing the generalization of deep neural networks.
To demonstrate the generalizability of the proposed framework across different tasks and population demographics.

Main Methods:

A normalizing flow network is trained to capture the distribution characteristics of a target source domain.
A shallow harmonizer network is trained to reconstruct source domain images from augmented counterparts.
During inference, the harmonizer is updated to ensure output images conform to the learned source domain distribution modeled by the normalizing flow network.

Main Results:

The proposed unsupervised harmonization framework successfully aligns MR images to a desired source domain distribution.
The method demonstrated superior performance in cross-domain brain MRI segmentation for both adults and neonates.
Effective application in neonatal brain age estimation highlights its generalizability across diverse tasks and demographics.

Conclusions:

The novel unsupervised, source-free, and task-agnostic harmonization framework effectively addresses MR image heterogeneity.
The normalizing flows-based approach significantly improves the generalization of deep neural networks for medical image analysis tasks.
This methodology offers a robust solution for enhancing the reliability and applicability of AI models in diverse clinical settings.