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

Serum Galectin-9 and Decorin in relation to brain aging and the green-Mediterranean diet: A secondary analysis of the DIRECT PLUS randomized trial.

Clinical nutrition (Edinburgh, Scotland)·2025
Same author

Hyperfusion: A hypernetwork approach to multimodal integration of tabular and medical imaging data for predictive modeling.

Medical image analysis·2025
Same author

Fine hippocampal morphology analysis with a multi-dataset cross-sectional study on 2911 subjects.

NeuroImage. Clinical·2024
Same author

Deep learning-based BMI inference from structural brain MRI reflects brain alterations following lifestyle intervention.

Human brain mapping·2024
Same author

Fine scale hippocampus morphology variation cross 552 healthy subjects from age 20 to 80.

Frontiers in neuroscience·2023
Same author

Differentiable Histogram Loss Functions for Intensity-based Image-to-Image Translation.

IEEE transactions on pattern analysis and machine intelligence·2023

Related Experiment Video

Updated: Dec 17, 2025

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
06:52

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

2.6K

Subsampled brain MRI reconstruction by generative adversarial neural networks.

Roy Shaul1, Itamar David1, Ohad Shitrit1

  • 1The School of Electrical and Computer Engineering The Zlotowski Center for Neuroscience Ben-Gurion University of the Negev, Israel.

Medical Image Analysis
|June 29, 2020
PubMed
Summary

This study introduces a deep learning framework to accelerate magnetic resonance imaging (MRI) scans by reconstructing undersampled data. The AI-powered method significantly improves scan speed without compromising image quality or clinical usability.

Keywords:
Deep learningGANsK-space subsamplingMRI reconstruction

More Related Videos

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol
10:14

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

7.6K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.3K

Related Experiment Videos

Last Updated: Dec 17, 2025

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
06:52

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

2.6K
3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol
10:14

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

7.6K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Deep Learning

Background:

  • Accelerating magnetic resonance imaging (MRI) scan times is crucial for patient comfort, cost reduction, and time-sensitive applications like fetal, cardiac, and functional MRI.
  • Current acceleration techniques often compromise spatial resolution or require expensive hardware.
  • Faster MRI acquisition is vital for reducing motion artifacts in dynamic imaging scenarios.

Purpose of the Study:

  • To develop a practical, software-only deep learning framework for accelerating MRI acquisition.
  • To maintain diagnostically relevant image quality despite significant undersampling.
  • To validate the clinical utility of reconstructed MRI scans through segmentation and pharmacokinetic parameter analysis.

Main Methods:

  • Employed a deep learning framework utilizing generative adversarial neural networks (GANs) for MRI reconstruction.
  • Implemented a strategy of MRI k-space subsampling followed by AI-driven estimation of missing data.
  • Incorporated adversarial, fidelity, and image-quality losses for optimizing the reconstruction process.

Main Results:

  • Achieved up to fivefold acceleration in diverse brain MRI datasets, including healthy adults, multiple sclerosis patients, and dynamic contrast-enhanced MRI (DCE-MRI) scans.
  • Demonstrated superior performance over state-of-the-art methods in peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE) for pharmacokinetic parameters.
  • Validated clinical usability via segmentation compatibility (Dice scores, Hausdorff distance) and accurate pharmacokinetic parameter calculation.

Conclusions:

  • The proposed deep learning-based MRI reconstruction framework effectively accelerates scan times while preserving image quality and clinical utility.
  • This software-only approach offers a practical solution for enhancing MRI efficiency across various clinical applications.
  • The method outperforms existing techniques, paving the way for faster and more accessible MRI diagnostics.