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

Effect of basis choice on quantitative parameter estimation in accelerated subspace reconstructions.

Magnetic resonance letters·2026
Same author

Multiphysics Analysis and Optimization of a Thin-Film Lithium Niobate Phase Modulator for Fiber-Optic Gyroscopes.

Micromachines·2026
Same author

Hepatocellular Carcinoma Precursor Lesions: From Pathological Basis to Risk Stratification and Precision Intervention.

Journal of hepatocellular carcinoma·2026
Same author

Age-Specific Contrast Optimization of bSSFP in Fetal Brain.

Magnetic resonance in medicine·2026
Same author

A spatiotemporal dependency-aware lightweight CNN-ViT network for 3D MRF with a balanced acceleration strategy.

Medical image analysis·2026
Same author

Smart single hollow magnetothermal nanorings with phase change materials for controlled drug release and negative MRI guided cancer therapy.

International journal of pharmaceutics·2026

Related Experiment Video

Updated: Sep 21, 2025

Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics
08:48

Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics

Published on: January 9, 2016

7.0K

MOdel-Based SyntheTic Data-Driven Learning (MOST-DL): Application in Single-Shot T2 Mapping With Severe Head Motion

Qinqin Yang, Yanhong Lin, Jiechao Wang

    IEEE Transactions on Medical Imaging
    |June 3, 2022
    PubMed
    Summary

    Synthetic data aids deep learning in magnetic resonance imaging (MRI). A new framework, MOST-DL, bridges the domain gap, enabling motion-robust quantitative mapping even with limited real-world data.

    More Related Videos

    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
    08:45

    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

    Published on: October 24, 2012

    14.8K
    Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments
    07:52

    Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

    Published on: June 28, 2024

    1.3K

    Related Experiment Videos

    Last Updated: Sep 21, 2025

    Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics
    08:48

    Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics

    Published on: January 9, 2016

    7.0K
    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
    08:45

    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

    Published on: October 24, 2012

    14.8K
    Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments
    07:52

    Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

    Published on: June 28, 2024

    1.3K

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Biophysics

    Background:

    • Deep learning in MRI requires large datasets, often unavailable.
    • Synthetic data offers a solution but faces domain gap challenges.
    • Motion artifacts degrade quantitative MRI accuracy.

    Purpose of the Study:

    • To develop a framework (MOST-DL) for training deep learning models with synthetic data for MRI.
    • To achieve motion-robust quantitative mapping using ultra-fast MRI.
    • To bridge the domain gap between synthetic and real MRI data.

    Main Methods:

    • Combined Bloch simulation and general MRI models for synthetic data generation.
    • Developed a MOST-DL framework integrating calibrationless parallel reconstruction and intra-shot motion correction.
    • Incorporated realistic textures and imperfection simulations to bridge the domain gap.
    • Trained neural networks with synthetic data and validated on in vivo human brain scans.

    Main Results:

    • MOST-DL significantly reduced ghosting and motion artifacts in quantitative mapping.
    • The framework demonstrated robustness against unpredictable subject movement.
    • Successful application in motion-robust quantitative mapping using single-shot overlapping-echo acquisition.

    Conclusions:

    • MOST-DL effectively addresses the lack of training data in supervised deep learning for MRI.
    • The proposed method shows potential for clinical application in motion-prone patients.
    • This framework enhances the reliability of quantitative MRI under challenging conditions.