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

Environment and reproductive health in China: challenges and opportunities.

Environmental health perspectives·2012
Same author

Posttransplant mortality risk assessment for adult-to-adult right-lobe living donor liver recipients with benign end-stage liver disease.

Scandinavian journal of gastroenterology·2012
Same author

Sodium nitrite protects against kidney injury induced by brain death and improves post-transplant function.

Kidney international·2012
Same author

OIC-A006-loaded true bone ceramic heals rabbit critical-sized segmental radial defect.

Die Pharmazie·2012
Same author

Liquid chromatography-mass spectrometric multiple reaction monitoring-based strategies for expanding targeted profiling towards quantitative metabolomics.

Current drug metabolism·2012
Same author

Structural and functional characterization of mature forms of metalloprotease E495 from Arctic sea-ice bacterium Pseudoalteromonas sp. SM495.

PloS one·2012

Related Experiment Video

Updated: Dec 5, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

2.0K

Multislice left ventricular ejection fraction prediction from cardiac MRIs without segmentation using shared

Zhi Liu1, Yihao Zhang1, Weiwei Li2

  • 1School of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|October 18, 2020
PubMed
Summary

We developed SptDenNet, a novel deep learning model for cardiac MRI analysis. This efficient, end-to-end framework accurately predicts left ventricular ejection fraction without segmentation, achieving comparable results to state-of-the-art methods.

Keywords:
Cardiac MRIsEjection fractionLV QuantificationLV segmentationSpatiotemporal features

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

6.9K
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

14.7K

Related Experiment Videos

Last Updated: Dec 5, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

2.0K
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

6.9K
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

14.7K

Area of Science:

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

Background:

  • Accurate assessment of cardiac function, particularly left ventricular ejection fraction (LVEF), is crucial for diagnosing and managing cardiovascular diseases.
  • Traditional methods for LVEF calculation from cardiac magnetic resonance images (MRI) often require manual segmentation, which is time-consuming and prone to inter-observer variability.
  • Developing automated, efficient, and accurate methods for LVEF prediction from cardiac MRI is a significant clinical need.

Purpose of the Study:

  • To propose SptDenNet, a novel spatiotemporal deep learning model for the direct prediction of LVEF from cardiac MRI.
  • To develop an end-to-end framework that simultaneously extracts spatial and temporal features from cardiac MRI to exploit 3D information over the cardiac cycle.
  • To evaluate the performance and efficiency of SptDenNet compared to existing state-of-the-art methods, particularly in its ability to bypass the need for image segmentation.

Main Methods:

  • The SptDenNet model, based on DenseNet architecture, was designed to process individual frames of short-axis (SAX) view cardiac MRI slices to extract spatiotemporal features.
  • A shared end-to-end framework was implemented, concatenating features from all selected SAX slices for direct LVEF prediction using fully connected and softmax layers.
  • The FocalLoss function was employed to address class imbalance issues inherent in medical imaging datasets.

Main Results:

  • The SptDenNet framework achieved an average mean absolute error (MAE) of 6.84 for LVEF prediction on the Second Annual Data Science Bowl dataset, demonstrating performance comparable to state-of-the-art end-to-end approaches without segmentation.
  • When applied to 4-chamber view images from the same dataset for cardiac function prediction, the model achieved an accuracy of 86.07%.
  • The proposed approach proved computationally efficient and reduced manual workload by eliminating the need for image segmentation.

Conclusions:

  • SptDenNet offers an effective and efficient end-to-end solution for automated LVEF prediction from cardiac MRI.
  • The model's ability to directly predict LVEF without segmentation simplifies the analysis workflow and reduces potential errors associated with manual segmentation.
  • The spatiotemporal feature extraction capabilities of SptDenNet demonstrate its potential for advancing automated cardiac function assessment in clinical practice.