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

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...

You might also read

Related Articles

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

Sort by
Same author

Restoration of 3-dimensional aortic hemodynamics after the Ross procedure for unicuspid aortic valve disease using 4-dimensional flow magnetic resonance imaging.

JTCVS structural and endovascular·2026
Same author

Corrigendum to "4D Flow cardiovascular magnetic resonance consensus statement: 2023 update" [Journal of Cardiovascular Magnetic Resonance 25 (2023) 40].

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2026
Same author

Tandem extracorporeal blood purification therapies for sepsis and acute kidney injury in critically ill children: a state-of-the-art review.

Renal failure·2026
Same author

Pterostilbene in the Management and Treatment of Multiple Myeloma.

Current issues in molecular biology·2026
Same author

ACR Appropriateness Criteria® Evaluation of Cardiac Masses.

Journal of the American College of Radiology : JACR·2026
Same author

Multiparametric CMR for detection of cardiac amyloidosis in patients with undifferentiated concentric left ventricular hypertrophy.

The international journal of cardiovascular imaging·2026

Related Experiment Video

Updated: Jul 9, 2026

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

CE-MRA-FLOWnet: Fast and Accurate Generative AI-Based Aortic Hemodynamic Mapping from Contrast-Enhanced MRA.

David Dushfunian1, Haben Berhane2, Ethan Johnson1

  • 1Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.

Journal of Cardiovascular Magnetic Resonance : Official Journal of the Society for Cardiovascular Magnetic Resonance
|July 7, 2026
PubMed
Summary

A new AI model, CE-MRA-FLOWnet, accurately predicts thoracic aortic disease (TAD) hemodynamics from standard MRI scans. This innovation promises to improve risk assessment for TAD patients by providing crucial hemodynamic data more accessibly.

Keywords:
4D flow MRIAIaortacontrast-enhanced MRAgenerative adversarial networkshemodynamics

More Related Videos

A Magnetic Resonance Imaging-based Computational Protocol for Analysis of Plaque Morphology and Hemodynamics in Patients with Carotid Artery Stenosis
09:36

A Magnetic Resonance Imaging-based Computational Protocol for Analysis of Plaque Morphology and Hemodynamics in Patients with Carotid Artery Stenosis

Published on: August 12, 2025

Related Experiment Videos

Last Updated: Jul 9, 2026

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

A Magnetic Resonance Imaging-based Computational Protocol for Analysis of Plaque Morphology and Hemodynamics in Patients with Carotid Artery Stenosis
09:36

A Magnetic Resonance Imaging-based Computational Protocol for Analysis of Plaque Morphology and Hemodynamics in Patients with Carotid Artery Stenosis

Published on: August 12, 2025

Area of Science:

  • Cardiovascular Imaging
  • Artificial Intelligence in Medicine
  • Biomedical Engineering

Background:

  • Thoracic aortic disease (TAD) risk stratification traditionally relies on aortic diameter, which is an imperfect measure.
  • 4D flow MRI provides valuable hemodynamic biomarkers like peak velocity (PV) and wall shear stress (WSS) but faces limitations in clinical adoption due to scan time and complexity.
  • There is a need for accessible methods to assess aortic hemodynamics for improved TAD risk stratification.

Purpose of the Study:

  • To develop and validate a fluid-physics informed deep generative adversarial neural network (CE-MRA-FLOWnet) for predicting aortic hemodynamics.
  • To enable hemodynamic prediction directly from standard contrast-enhanced magnetic resonance angiography (CE-MRA) images.
  • To assess the clinical utility of AI-derived hemodynamic metrics for risk stratification in TAD patients.

Main Methods:

  • Retrospective analysis of 1392 patients with suspected TAD who underwent paired 4D flow MRI and CE-MRA.
  • CE-MRA-FLOWnet was trained on CE-MRA data to predict 3D blood flow velocity vector fields, serving as a surrogate for 4D flow MRI.
  • Comparison of AI-derived PV, WSS, and aortic valve stenosis severity with 4D flow MRI ground truth; assessment of predictive value for adverse outcomes in a BAV subgroup.

Main Results:

  • CE-MRA-FLOWnet demonstrated rapid inference times (0.88 seconds) after an 8100-minute training period.
  • AI-derived PV and WSS showed strong agreement and minimal bias compared to 4D flow MRI measurements.
  • CE-MRA-FLOWnet-derived hemodynamic metrics outperformed aortic diameter in predicting adverse outcomes (WSS AUC = 0.83-0.88).

Conclusions:

  • CE-MRA-FLOWnet accurately predicts aortic hemodynamics in TAD patients using readily available CE-MRA images.
  • The AI model provides near real-time hemodynamic data, overcoming limitations of traditional 4D flow MRI.
  • This technology holds significant potential for widespread clinical integration to enhance TAD risk stratification and patient management.