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

Mitral Valve Prolapse I: Introduction01:27

Mitral Valve Prolapse I: Introduction

IntroductionThe mitral valve, one of the heart's four valves, regulates blood flow. These valves have flaps that open and close to direct blood properly through the heart and body. During each heartbeat, the flaps open for blood to pass through and seal shut to prevent backflow. Specifically, the mitral valve opens to allow blood flow from the heart's upper left chamber to the lower left chamber. It then closes securely as the lower left chamber contracts to pump blood to the body, preventing...

You might also read

Related Articles

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

Sort by
Same author

Determinants of Impaired Left Atrial Hemodynamics in Paroxysmal Atrial Fibrillation: A 4D Flow MRI Study.

Journal of imaging·2026
Same author

REPLY: Beyond Global Viability: Patient-Specific Identification of Jeopardized Myocardium to Guide Revascularization.

JACC. Cardiovascular imaging·2026
Same author

Machine Learning Model Using Pre-Cancer Therapy Cardiac Magnetic Resonance Images to Predict Cancer Therapy-Related Cardiac Dysfunction.

JACC. Cardiovascular imaging·2026
Same author

Predictors of Long-Term Outcomes in Hypertrophic Cardiomyopathy: The NHLBI HCM Registry.

JAMA·2026
Same author

Patient-Specific Registration of Segmental Jeopardy and Viability: Novel Method to Guide Revascularization in Ischemic Cardiomyopathy.

JACC. Cardiovascular imaging·2026
Same author

4D Digital Heart Model-Guided Left and Right Ventricular Lead Placement for Cardiac Resynchronization Therapy: Results of MAPIT-CRT Trial.

Circulation. Arrhythmia and electrophysiology·2025

Related Experiment Video

Updated: Jun 24, 2026

Quantification of Global Diastolic Function by Kinematic Modeling-based Analysis of Transmitral Flow via the Parametrized Diastolic Filling Formalism
11:04

Quantification of Global Diastolic Function by Kinematic Modeling-based Analysis of Transmitral Flow via the Parametrized Diastolic Filling Formalism

Published on: September 1, 2014

11.4K

Aortic and mitral flow quantification using dynamic valve tracking and machine learning: Prospective study assessing

Julio Garcia1,2,3,4,5, Kailey Beckie1,2,3,4, Ali F Hassanabad1,2

  • 1Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada.

JRSM Cardiovascular Disease
|March 15, 2021
PubMed
Summary

Machine learning automates the detection and tracking of aortic and mitral valve planes in 4D flow MRI, enabling efficient quantification of blood flow and hemodynamics in heart valve disease assessment.

Keywords:
4D-flow magnetic resonance imagingBicuspid aortic valvemachine learningmitral valvevalve tracking

More Related Videos

Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice
12:12

Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice

Published on: February 14, 2017

16.4K
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

3.6K

Related Experiment Videos

Last Updated: Jun 24, 2026

Quantification of Global Diastolic Function by Kinematic Modeling-based Analysis of Transmitral Flow via the Parametrized Diastolic Filling Formalism
11:04

Quantification of Global Diastolic Function by Kinematic Modeling-based Analysis of Transmitral Flow via the Parametrized Diastolic Filling Formalism

Published on: September 1, 2014

11.4K
Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice
12:12

Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice

Published on: February 14, 2017

16.4K
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

3.6K

Area of Science:

  • Cardiovascular Imaging
  • Medical Physics
  • Biomedical Engineering

Background:

  • Accurate blood flow assessment is vital for diagnosing heart valve disease.
  • Time-resolved 4D flow MRI offers comprehensive hemodynamic analysis but often requires manual plane definition.
  • Automating valve plane detection in 4D flow MRI can improve efficiency and accuracy.

Purpose of the Study:

  • To demonstrate the feasibility of automated detection and tracking of aortic and mitral valve planes using 4D flow MRI.
  • To assess blood flow parameters including flow volume, regurgitant fraction, and peak velocity.
  • To evaluate the accuracy and reproducibility of the automated method.

Main Methods:

  • A prospective study enrolled 106 subjects (19 mitral disease, 65 aortic disease, 22 controls).
  • Machine learning was utilized to detect aortic and mitral valve locations and motion in cine three-chamber views.
  • Co-registration of perpendicular projections to 4D flow MRI datasets allowed for hemodynamic quantification.

Main Results:

  • Elevated aortic regurgitant fraction was observed in aortic valve disease patients compared to controls and mitral valve disease patients.
  • Mitral regurgitant fraction was significantly higher in mitral valve disease patients.
  • The automated method showed good correlation (r > 0.6) for aortic total flow and peak velocity, and mitral peak velocity and regurgitant fraction, with excellent reproducibility.

Conclusions:

  • Automated valve plane detection using machine learning facilitates efficient quantification of aortic and mitral hemodynamics from 4D flow MRI.
  • This approach enhances the assessment of blood flow in patients with heart valve disease.
  • The study confirms the reliability and reproducibility of machine learning-assisted valve plane analysis in cardiovascular imaging.