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

5.4K
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...
5.4K

You might also read

Related Articles

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

Sort by
Same author

Inferring and evaluating network medicine-based disease modules with nextflow.

Bioinformatics (Oxford, England)·2026
Same author

Generating Alzheimer's narratives using large language models.

BMC medical informatics and decision making·2026
Same author

Pushing the boundaries of robotic computed tomography: automated twin-robot CT scan with maximum reachability.

Scientific reports·2026
Same author

Clinical Evaluation of Deep Learning-Reconstructed Postcontrast 3D T1-Weighted Volume Interpolated Breath-Hold Examination (VIBE) Compared with Standard VIBE for Detection of Internal Auditory Canal Lesions.

AJNR. American journal of neuroradiology·2026
Same author

Synthesizing vocal tract magnetic resonance imaging sequences with phoneme-aware diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Illuminating the black box of reservoir computing.

Scientific reports·2026

Related Experiment Video

Updated: Aug 19, 2025

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

Deep learning-based motion quantification from k-space for fast model-based magnetic resonance imaging motion

Julian Hossbach1,2, Daniel Nicolas Splitthoff2, Stephen Cauley3

  • 1Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.

Medical Physics
|November 26, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning method for fast and robust head motion correction in MRI scans. The MoPED algorithm significantly reduces computation time and improves image quality without causing image artifacts.

Keywords:
MRI motion correctiondeep learningmotion estimation

More Related Videos

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.6K
Quantifying Mixing using Magnetic Resonance Imaging
07:33

Quantifying Mixing using Magnetic Resonance Imaging

Published on: January 25, 2012

11.0K

Related Experiment Videos

Last Updated: Aug 19, 2025

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
Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.6K
Quantifying Mixing using Magnetic Resonance Imaging
07:33

Quantifying Mixing using Magnetic Resonance Imaging

Published on: January 25, 2012

11.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Intra-scan rigid-body motion is a significant challenge in head MRI, impacting image quality and clinical utility.
  • Existing retrospective motion correction methods are often computationally intensive or can introduce image artifacts (hallucinations).

Purpose of the Study:

  • To develop a novel, fast, and robust retrospective rigid-body motion correction method for MRI.
  • To combine classical model-driven approaches with a deep learning algorithm for improved motion correction.

Main Methods:

  • A deep learning network, Motion Parameter Estimating Densenet (MoPED), was developed to estimate slice-wise 2D rigid in-plane motion parameters.
  • MoPED utilizes DenseBlocks and multitask learning, processing motion-corrupted k-space data and a low-resolution reference scan.
  • The method was integrated into an iterative data-consistency (DC)-driven algorithm for motion correction, evaluated using simulated and in-vivo data.

Main Results:

  • MoPED achieved a high correlation (0.968) with simulated ground-truth motion parameters.
  • In-silico tests showed a ~27x reduction in optimization time and >2x decrease in RMSE and DC error compared to conventional methods.
  • In-vivo experiments demonstrated a ~20x reduction in computation time, improved RMSE (0.055 to 0.033), and increased SSIM (0.795 to 0.862), with no observed hallucinations.

Conclusions:

  • Integrating deep learning into model-based motion correction significantly enhances optimization and computation speed.
  • The k-space-based estimation ensures data-consistent correction, effectively preventing hallucinations common in image-to-image deep learning approaches.