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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

7.8K
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...
7.8K

You might also read

Related Articles

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

Sort by
Same author

Enhanced detection of subtle cortical abnormalities in focal epilepsy using 7 T MRI surface-based models and graph neural networks.

Neuroradiology·2026
Same author

A deep-learning framework reveals whole-body perturbations at cell level.

Nature·2026
Same author

3D Brachial Plexus Neurography With Variable-Rate Selective Excitation RF Pulses.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Susceptibility-weighted imaging in patients with Corticobasal Syndrome or Progressive Supranuclear Palsy: distribution of iron deposits reflects clinical symptoms in 4-R tauopathies.

AJNR. American journal of neuroradiology·2026
Same author

A MR Fingerprinting Development Kit for Quantitative 3D Brain Imaging.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Generalist foundation models from a multimodal dataset for 3D computed tomography.

Nature biomedical engineering·2026

Related Experiment Video

Updated: Oct 3, 2025

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.7K

Learning residual motion correction for fast and robust 3D multiparametric MRI.

Carolin M Pirkl1, Matteo Cencini2, Jan W Kurzawski3

  • 1Department of Computer Science, Technical University of Munich, Garching, Germany; GE Healthcare, Munich, Germany.

Medical Image Analysis
|February 18, 2022
PubMed
Summary

This study introduces a novel deep learning method for correcting patient motion artifacts in Magnetic Resonance Imaging (MRI). The technique significantly improves image quality, making more MRI data diagnostically usable.

Keywords:
3D Motion correctionMultiparametric MRIMultiscale CNNResidual learning

More Related Videos

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
3D Cine Magnetic Resonance Imaging of Respiratory Motion in Mechanically Ventilated Mice and Rats
08:22

3D Cine Magnetic Resonance Imaging of Respiratory Motion in Mechanically Ventilated Mice and Rats

Published on: September 19, 2025

309

Related Experiment Videos

Last Updated: Oct 3, 2025

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.7K
Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
3D Cine Magnetic Resonance Imaging of Respiratory Motion in Mechanically Ventilated Mice and Rats
08:22

3D Cine Magnetic Resonance Imaging of Respiratory Motion in Mechanically Ventilated Mice and Rats

Published on: September 19, 2025

309

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Neuroimaging

Background:

  • Patient motion is a significant challenge in Magnetic Resonance Imaging (MRI), degrading data quality and impacting quantitative parameter estimation.
  • Existing motion correction methods are insufficient for clinical routine, particularly for multiparametric whole-brain imaging.
  • Motion artifacts disrupt magnetization dynamics, leading to inaccuracies in quantitative MRI parameter estimation.

Purpose of the Study:

  • To develop and evaluate a novel retrospective motion correction strategy for fast 3D whole-brain multiparametric MRI using residual learning.
  • To address the challenge of limited data availability for supervised learning by proposing a physics-informed simulation for dataset generation.
  • To demonstrate the effectiveness and generalization capabilities of the proposed method across various motion levels and patient populations.

Main Methods:

  • A 3D multiscale convolutional neural network (CNN) was designed to learn the relationship between motion-affected and motion-free quantitative parameter maps.
  • A physics-informed simulation approach was employed to generate paired datasets for supervised training, overcoming data limitations.
  • The method was evaluated using 3D Quantitative Transient-state Imaging at 1.5T and 3T, assessing performance on simulated and real in vivo motion data.

Main Results:

  • The proposed residual learning CNN effectively corrected motion artifacts in quantitative parameter maps.
  • The method demonstrated robustness across various motion intensities and generalized well to real-world in vivo data from healthy volunteers and diverse patient cases.
  • Performance evaluation showed superior motion correction compared to state-of-the-art techniques, yielding clinically relevant image quality even with significant patient movement.

Conclusions:

  • The novel residual learning-based motion correction strategy significantly enhances image quality in multiparametric MRI.
  • This approach improves the diagnostic utility of MRI data, reducing the need to discard motion-affected scans.
  • The method holds substantial clinical implications for improving MRI data acquisition and interpretation in routine practice.