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

5.1K
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...
5.1K

You might also read

Related Articles

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

Sort by
Same author

Association of Deep Learning-based Myocardial Infarction Size Quantification in Cardiac MRI with Cardiac Biomarker Levels.

Radiology. Cardiothoracic imaging·2026
Same author

BART Streams: Real-Time Reconstruction Using a Modular Framework for Pipeline Processing.

Magnetic resonance in medicine·2026
Same author

Fast Real-Time Cardiac MRI: a Review of Current Techniques and Future Directions.

Investigative magnetic resonance imaging·2026
Same author

Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm.

Magnetic resonance in medicine·2026
Same author

DARE: A Deformable Adaptive Regularization Estimator for learning-based medical image registration.

Artificial intelligence in medicine·2026
Same author

FENCE: Flexible Electric Noise Reduction Endo-Shield for the Suppression of Electromagnetic Interference in Low-Field MRI.

NMR in biomedicine·2026

Related Experiment Video

Updated: Jun 18, 2025

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves
06:26

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

379

Self-supervised learning for improved calibrationless radial MRI with NLINV-Net.

Moritz Blumenthal1,2, Chiara Fantinato1, Christina Unterberg-Buchwald2,3,4

  • 1Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria.

Magnetic Resonance in Medicine
|July 31, 2024
PubMed
Summary

A new neural network, NLINV-Net, enables calibrationless MRI reconstruction without ground truth data. It significantly reduces noise and improves image quality in real-time cardiac and quantitative T1 mapping applications.

Keywords:
MRIimage reconstructionnonlinear inverse problemsparallel imagingself‐supervised learning

More Related Videos

In vivo 19F MRI for Cell Tracking
10:05

In vivo 19F MRI for Cell Tracking

Published on: November 25, 2013

14.7K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

3.3K

Related Experiment Videos

Last Updated: Jun 18, 2025

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves
06:26

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

379
In vivo 19F MRI for Cell Tracking
10:05

In vivo 19F MRI for Cell Tracking

Published on: November 25, 2013

14.7K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

3.3K

Area of Science:

  • Magnetic Resonance Imaging (MRI)
  • Artificial Intelligence in Medical Imaging
  • Image Reconstruction Algorithms

Background:

  • Calibrationless MRI reconstruction is crucial for applications lacking ground truth data.
  • Existing methods like nonlinear inversion (NLINV) and parallel imaging with compressed sensing (PI-CS) have limitations.

Purpose of the Study:

  • To develop NLINV-Net, a novel neural network for improved calibrationless reconstruction of radial MRI data.
  • To enable training without ground truth data using self-supervision via data undersampling (SSDU).

Main Methods:

  • NLINV-Net directly estimates images and coil sensitivities from k-space data using nonlinear inversion.
  • Self-supervision via data undersampling (SSDU) facilitates training without ground truth.
  • Region-optimized virtual (ROVir) coils were employed to suppress artifacts and focus the loss function.

Main Results:

  • NLINV-Net reconstructions demonstrated significantly reduced noise compared to conventional NLINV.
  • ROVir coils effectively suppressed streak artifacts, and focused loss improved temporal resolution in cardiac imaging.
  • Quantitative T1 maps showed comparable quality to PI-CS, without requiring slice-specific tuning.

Conclusions:

  • NLINV-Net offers a versatile solution for calibrationless MRI reconstruction.
  • The method is particularly valuable for challenging imaging scenarios where ground truth data is unavailable.