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

Physics-embedded CycleGAN for robust metabolite mapping in short-readout deuterium metabolic imaging.

Magnetic resonance letters·2026
Same author

A joint pilot optimization and channel estimation algorithm based on CBAM-CNN for multipath fading environments in underground coal mines.

Scientific reports·2026
Same author

Targeting the PINK1/Parkin-FNDC5 pathway: a novel mechanism of icariin in regulating muscle-bone metabolic coupling in osteosarcopenia.

Journal of translational medicine·2026
Same author

Exploring the impact of childhood obesity on sarcopenia-related traits: A 2-way Mendelian randomization analysis.

Medicine·2026
Same author

Deciphering the role of commercial nanofiltration membranes in removing 30 per-and polyfluoroalkyl substances: performances, mechanisms and implications.

Environmental technology·2026
Same author

Phase Model-Driven Deep Learning for Robust Phase Correction in High-Throughput NMR-Based Metabolomics.

The journal of physical chemistry letters·2026

Related Experiment Video

Updated: May 24, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

404

MRI Motion Correction Through Disentangled CycleGAN Based on Multi-Mask K-Space Subsampling.

Gang Chen, Han Xie, Xinglong Rao

    IEEE Transactions on Medical Imaging
    |March 3, 2025
    PubMed
    Summary

    A new method, DCGAN-MS, uses multi-mask k-space subsampling to correct motion artifacts in MRI scans. This approach disentangles images, improving clarity and efficiency for better diagnostic imaging.

    More Related Videos

    Optogenetic Functional MRI
    06:06

    Optogenetic Functional MRI

    Published on: April 19, 2016

    14.7K
    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
    10:06

    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

    Published on: May 10, 2012

    12.8K

    Related Experiment Videos

    Last Updated: May 24, 2025

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
    10:44

    Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

    Published on: June 21, 2024

    404
    Optogenetic Functional MRI
    06:06

    Optogenetic Functional MRI

    Published on: April 19, 2016

    14.7K
    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
    10:06

    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

    Published on: May 10, 2012

    12.8K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Image Processing

    Background:

    • Motion artifacts are a significant challenge in MRI, degrading image quality and potentially leading to misdiagnosis.
    • Existing retrospective motion correction methods often struggle with complex artifact patterns and computational demands.

    Purpose of the Study:

    • To introduce DCGAN-MS, a novel retrospective motion correction technique for MRI.
    • To address the image domain translation challenge posed by motion artifacts using a disentangled CycleGAN architecture.

    Main Methods:

    • DCGAN-MS employs multi-mask k-space subsampling to reduce motion artifact complexity by selectively discarding corrupted k-space lines.
    • The network utilizes specialized encoders to disentangle motion-corrupted images into content and artifact features.
    • Motion-corrected images are generated by decoding the extracted content features.

    Main Results:

    • DCGAN-MS demonstrated effective motion artifact correction across diverse MRI datasets, including human liver, human brain (fastMRI), and preclinical rodent brain.
    • Significant quantitative improvements were observed: SSIM increased from 0.75 to 0.86 (human liver) and 0.72 to 0.82 (rodent brain).
    • PSNR values rose from 26.09 to 31.09 and 25.10 to 31.77, respectively. Performance was further validated using KID and FID metrics.

    Conclusions:

    • DCGAN-MS offers an efficient and effective solution for retrospective motion correction in MRI.
    • The multi-mask k-space subsampling strategy enhances network performance by creating sparser artifact features.
    • The method shows strong potential for improving the diagnostic utility of clinical and preclinical MRI scans.