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

Wellness Works: A Longitudinal Approach to Promoting Radiology Program Director Wellness and Community through the Development of Peer Mentorship Groups.

Academic radiology·2026
Same author

Initial Despair and Current Hope of Identifying a Clinically Useful Treatment of Myocardial Reperfusion Injury: Insights Derived from Studies of Platelet P2Y<sub>12</sub> Antagonists and Interference with Inflammation and NLRP3 Assembly.

International journal of molecular sciences·2024
Same author

Automated segmentation of the left-ventricle from MRI with a fully convolutional network to investigate CTRCD in breast cancer patients.

Journal of medical imaging (Bellingham, Wash.)·2024
Same author

Gamma secretase activating protein promotes end-organ dysfunction after bacterial pneumonia.

American journal of physiology. Lung cellular and molecular physiology·2023
Same author

Lethal Caspase-1/4-Dependent Injury Occurs in the First Minutes of Coronary Reperfusion and Requires Calpain Activity.

International journal of molecular sciences·2023
Same author

Can global longitudinal strain (GLS) with magnetic resonance prognosticate early cancer therapy-related cardiac dysfunction (CTRCD) in breast cancer patients, a prospective study?

Magnetic resonance imaging·2022

Related Experiment Video

Updated: Oct 11, 2025

Transthoracic Speckle Tracking Echocardiography for the Quantitative Assessment of Left Ventricular Myocardial Deformation
09:05

Transthoracic Speckle Tracking Echocardiography for the Quantitative Assessment of Left Ventricular Myocardial Deformation

Published on: October 20, 2016

19.8K

Direct left-ventricular global longitudinal strain (GLS) computation with a fully convolutional network.

Julia Kar1, Michael V Cohen2, Samuel A McQuiston3

  • 1Departments of Mechanical Engineering and Pharmacology, University of South Alabama, 150 Jaguar Drive, Mobile, AL 36688, United States.

Journal of Biomechanics
|December 6, 2021
PubMed
Summary
This summary is machine-generated.

A novel deep-learning method accurately computes global longitudinal strain (GLS) from cardiac MRI, aiding early detection of left-ventricular (LV) cardiotoxicity in breast cancer patients.

Keywords:
CardiotoxicityDENSEDeep-learningFully convolutional networkPhase-unwrapping

More Related Videos

Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging
11:13

Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging

Published on: May 24, 2021

6.6K
Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.2K

Related Experiment Videos

Last Updated: Oct 11, 2025

Transthoracic Speckle Tracking Echocardiography for the Quantitative Assessment of Left Ventricular Myocardial Deformation
09:05

Transthoracic Speckle Tracking Echocardiography for the Quantitative Assessment of Left Ventricular Myocardial Deformation

Published on: October 20, 2016

19.8K
Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging
11:13

Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging

Published on: May 24, 2021

6.6K
Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
06:34

Evaluation of Left Ventricular Structure and Function using 3D Echocardiography

Published on: October 28, 2020

4.2K

Area of Science:

  • Cardiovascular Imaging
  • Artificial Intelligence in Medicine
  • Medical Image Analysis

Background:

  • Global longitudinal strain (GLS) is crucial for detecting left-ventricular (LV) cardiotoxicity in breast cancer patients.
  • Current methods for GLS computation can be complex and time-consuming.
  • Deep learning offers potential for automating and improving cardiac image analysis.

Purpose of the Study:

  • To develop and validate a direct MRI-based, deep-learning semantic segmentation approach for computing GLS.
  • To assess the accuracy and reliability of this deep-learning method compared to existing techniques.

Main Methods:

  • A DeepLabV3+ fully convolutional network (FCN) was used to unwrap cardiac image phases from Displacement Encoding with Stimulated Echoes (DENSE) sequences.
  • Myocardial strains, including GLS, were computed from unwrapped phases using the Radial Point Interpolation Method.
  • The FCN method was validated against phantom data and human subject data, comparing results with quality-guided phase-unwrapping (QGPU) and robust transport of intensity equation (RTIE) methods.

Main Results:

  • The FCN demonstrated high accuracy in phase unwrapping, with low Mean Squared Error (MSE) on phantom data (1.6) compared to QGPU (2.7) and RTIE (6.1).
  • Classification accuracies on human LV data were excellent, with F1 scores of 0.95 (Dice 0.96) for FCN versus 0.94 (Dice 0.95) for RTIE.
  • GLS results derived from FCN and RTIE were highly comparable in both breast cancer patients (-16 ± 3%) and healthy subjects (-20 ± 3%), with a high intraclass correlation coefficient (C-α = 0.9).

Conclusions:

  • The developed deep-learning methodology provides an accurate and reliable approach for phase unwrapping in medical images.
  • This FCN-based method enables efficient and precise computation of GLS, supporting the early detection of cardiotoxicity.
  • The study validates a novel deep-learning application in cardiovascular imaging for improved patient monitoring.