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

4.8K
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...
4.8K

You might also read

Related Articles

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

Sort by
Same author

Feasibility of Golden Angle Spiral Real-Time Phase Contrast MRI at 0.55T: A Single-Center Prospective Study.

Bioengineering (Basel, Switzerland)·2026
Same author

Prospective Respiratory Motion Correction Using Machine Learning and Pilot Tone (PROMPT) in Cardiac MRI.

Magnetic resonance in medicine·2025
Same author

Multi-dynamic deep image prior for cardiac MRI.

Magnetic resonance in medicine·2025
Same author

Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction.

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2025
Same author

Groupwise image registration with edge-based loss for low-SNR cardiac MRI.

Magnetic resonance in medicine·2025
Same author

MRI recovery with self-calibrated denoisers without fully-sampled data.

Magma (New York, N.Y.)·2024

Related Experiment Video

Updated: May 16, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K

An unsupervised method for MRI recovery: deep image prior with structured sparsity.

Muhammad Ahmad Sultan1, Chong Chen1,2, Yingmin Liu3

  • 1Biomedical Engineering, Ohio State University, Columbus, OH, 43210, USA.

Magma (New York, N.Y.)
|May 15, 2025
PubMed
Summary

A new unsupervised MRI reconstruction method, Deep Image Prior with Structured Sparsity (DISCUS), was developed. DISCUS shows superior performance in reconstructing images from undersampled data, outperforming existing techniques.

Keywords:
Cardiac MRIReconstructionUnsupervised learning

More Related Videos

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.7K

Related Experiment Videos

Last Updated: May 16, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.7K

Area of Science:

  • Medical Imaging
  • Magnetic Resonance Imaging (MRI)

Background:

  • Fully sampled k-space data acquisition in MRI can be time-consuming.
  • Developing efficient MRI reconstruction methods is crucial for clinical applications.

Purpose of the Study:

  • To propose and validate an unsupervised MRI reconstruction method that bypasses the need for fully sampled k-space data.
  • To introduce Deep Image Prior with Structured Sparsity (DISCUS) for improved MRI reconstruction.

Main Methods:

  • The DISCUS method extends Deep Image Prior (DIP) by incorporating group sparsity for temporal variation capture.
  • Validation involved simulations, comparisons with compressed sensing and DIP, and evaluations on retrospective and prospective undersampled LGE MRI data.

Main Results:

  • DISCUS demonstrated superior reconstruction quality compared to existing methods.
  • Quantitative metrics (NMSE, SSIM) and expert reader scores confirmed DISCUS's effectiveness.

Conclusions:

  • The validated unsupervised method, DISCUS, offers a promising solution for MRI reconstruction.
  • This approach is beneficial for applications where acquiring complete k-space data is challenging.