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 Experiment Video

Updated: Jul 17, 2026

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

EMBC Special Issue: Optimized Multi-Contrast Self-Supervised MRI Reconstruction using Learned k-space Partitioning.

Brenden Kadota, Charles Millard, Mark Chiew

    IEEE Transactions on Bio-Medical Engineering
    |July 15, 2026
    PubMed
    Summary

    This study introduces a novel self-supervised learning method for faster MRI scans. By using multiple image contrasts and optimizing data partitioning, it achieves higher image quality without needing fully sampled data for training.

    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

    Inter-Shot Motion Correction of Segmented 3D-GRASE ASL Perfusion Imaging With Self-Navigation and CAIPI.

    Magnetic resonance in medicine·2026
    Same author

    SelExNet: A Self-Supervised Physics-Informed Framework for Multi-Channel Joint RF and Gradient Waveform Optimization in 2D Spatially Selective Excitation.

    Magnetic resonance in medicine·2026
    Same author

    Learning a B<sub>0</sub> Shimming Model Using Deep Neural Networks.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Learned k-space Partitioning for Optimized Self-Supervised MRI Reconstruction.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Combined angiography and perfusion using radial imaging and arterial spin labeling with structural contrast.

    Magnetic resonance in medicine·2025
    Same author

    Few-shot learning for highly accelerated 3D time-of-flight MRA reconstruction.

    Magnetic resonance in medicine·2025

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Deep Learning

    Background:

    • Deep learning accelerates MRI by reconstructing images from undersampled data.
    • Current multi-contrast methods require fully sampled data for supervised training.
    • Self-supervised learning via data undersampling (SSDU) trains on undersampled data by partitioning k-space.

    Purpose of the Study:

    • To improve self-supervised MRI reconstruction using multi-contrast information and learned data partitioning.
    • To develop a framework that trains on multiple undersampled contrasts without fully sampled reference data.

    Main Methods:

    • Proposed a multi-contrast self-supervised learning framework for joint training on undersampled contrasts.
    • Introduced end-to-end learning of optimal self-supervised data partitioning for each contrast.

    More Related Videos

    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

    Pulmonary Structural MRI using Free-Breathing, Self-Gated Ultra-short Echo Time Imaging
    05:07

    Pulmonary Structural MRI using Free-Breathing, Self-Gated Ultra-short Echo Time Imaging

    Published on: September 6, 2024

    Related Experiment Videos

    Last Updated: Jul 17, 2026

    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

    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

    Pulmonary Structural MRI using Free-Breathing, Self-Gated Ultra-short Echo Time Imaging
    05:07

    Pulmonary Structural MRI using Free-Breathing, Self-Gated Ultra-short Echo Time Imaging

    Published on: September 6, 2024

  • Generated partitioning masks by sampling from a learned probability distribution.

    • Main Results:

    • Demonstrated improved reconstruction quality compared to single-contrast self-supervised methods on public multi-contrast MRI datasets.
    • Showcased enhanced reconstruction fidelity through learned k-space data partitioning.
    • Achieved higher image fidelity and potential for accelerated MRI protocols.

    Conclusions:

    • Multi-contrast reconstruction with learned partitioning enhances fidelity over single-contrast self-supervised MRI.
    • The method enables higher image fidelity and/or faster MRI scans without requiring fully sampled training data.