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

Incremental Prognostic Value of Cardiac Magnetic Resonance Beyond Biomarker Staging in Transthyretin Cardiac Amyloidosis.

European heart journal. Cardiovascular Imaging·2026
Same author

Computational modeling of left ventricular flow using PC-CMR-derived four-dimensional wall motion.

International journal of engineering science·2026
Same author

Impact of Concomitant Mitral Regurgitation in Moderate Aortic Stenosis: Assessment of Remodeling and Clinical Outcomes.

JACC. Cardiovascular imaging·2026
Same author

Automated echocardiographic detection of mitral valve prolapse and mitral regurgitation with video-based artificial intelligence algorithms.

European heart journal. Digital health·2026
Same author

Governing Privacy-Preserving Face Recognition in Transport Infrastructures: A Comprehensive Review.

Sensors (Basel, Switzerland)·2026
Same author

Redefining Right Ventricular Function: Incremental Prognostic Utility of Effective RVEF on CMR in Functional Tricuspid Regurgitation-A Multicenter Validation Study.

JACC. Cardiovascular imaging·2026

Related Experiment Video

Updated: Sep 28, 2025

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
07:21

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

14.5K

A machine learning model to estimate myocardial stiffness from EDPVR.

Hamed Babaei1, Emilio A Mendiola1, Sunder Neelakantan1

  • 1Department of Biomedical Engineering, Texas A&M University, College Station, TX, 77843, USA.

Scientific Reports
|April 1, 2022
PubMed
Summary

A new machine learning (ML) model accurately predicts passive myocardial mechanical properties using readily available cardiac imaging data. This approach bypasses time-consuming finite-element (FE) simulations for improved patient-specific cardiac disease assessment.

More Related Videos

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

13.8K
Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
06:18

Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery

Published on: December 6, 2024

714

Related Experiment Videos

Last Updated: Sep 28, 2025

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
07:21

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

14.5K
Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
12:09

Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations

Published on: January 8, 2013

13.8K
Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
06:18

Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery

Published on: December 6, 2024

714

Area of Science:

  • Cardiovascular Mechanics
  • Biomedical Engineering
  • Machine Learning in Medicine

Background:

  • In-vivo estimation of myocardial mechanical properties is crucial for diagnosing and managing cardiac diseases like myocardial infarction and heart failure with preserved ejection fraction.
  • Current finite-element (FE) inverse methods are computationally expensive and time-consuming, involving complex geometry reconstruction and iterative simulations.
  • There is a need for a more feasible and accurate method to assess patient-specific myocardial properties.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for direct prediction of passive myocardial mechanical properties.
  • To bypass the exhaustive steps of traditional FE inverse methods.
  • To improve patient-specific diagnosis and prognosis of cardiac diseases involving myocardial remodeling.

Main Methods:

  • A multi-layer feed-forward neural network (MFNN) was trained using a comprehensive dataset generated from synthesized rodent heart geometries and varying end-diastolic pressure-volume relationships (EDPVRs).
  • Geometric (e.g., left ventricular volume, endocardial area) and architectural (myofiber orientation) features, along with hemodynamic loading (EDPVR), were used as inputs.
  • Latin hypercube sampling generated 2500 training, validation, and testing examples. Permutation feature importance analysis was conducted.

Main Results:

  • The ML model accurately predicted myocardial stiffness parameters ([Formula: see text] and [Formula: see text]) associated with fiber direction ([Formula: see text] and [Formula: see text]).
  • Left ventricular volume and endocardial area were identified as critical geometric predictors.
  • Model predictions showed excellent agreement with ex-vivo mechanical testing data and patient-specific FE inverse modeling results.

Conclusions:

  • The developed ML model offers a feasible and accurate approach to estimate patient-specific myocardial mechanical properties.
  • This method bridges the gap between organ-level metrics (EDPVR) and intrinsic tissue-level properties.
  • The ML model provides incremental information for improved clinical assessment and prognosis of cardiac diseases.