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 Experiment Video

Updated: Jan 18, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

A Robust and Data-Efficient Deep Learning Model for Cardiac Assessment without Segmentation.

Conor M Artman1, Ricardo Henao2

  • 1AI Research Group, Lawrence Livermore National Laboratory, 7000, East Avenue, Livermore, 94550, California, United States.

Research Square
|November 22, 2024
PubMed
Summary
This summary is machine-generated.

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

Adaptive AI for Cardiovascular Event Adjudication: Cardiovascular Event Adjudication Across Different Definitions in the ODYSSEY OUTCOMES and EUCLID Trials.

Circulation·2026
Same author

HorusEye: a self-supervised foundation model for generalizable X-ray tomography restoration.

Nature computational science·2026
Same author

Lifetime Adverse Pregnancy Outcome History and Cardiovascular Risk.

Hypertension (Dallas, Tex. : 1979)·2026
Same author

Gradient Importance Learning for Incomplete Observations.

... International Conference on Learning Representations·2026
Same author

Learning Survival Distributions with the Asymmetric Laplace Distribution.

Proceedings of machine learning research·2025
Same author

Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants.

Neonatology·2025
Same journal

HIV Transmission Dynamics in Greater Mexico City are Shaped by Dense Spatial Mixing.

Research square·2026
Same journal

A UCP1-IRES-Cre Knock-In Mouse Enables Specific Brown Adipocyte Targeting Without CNS Off-Target Expression.

Research square·2026
Same journal

Precision RNAi for Fibrodysplasia Ossificans Progressiva: a combinatorial, unimolecular, allele selective approach.

Research square·2026
Same journal

Perceptions of end-of-life care quality among bereaved closest contacts of community-dwelling older Australians: a cross-sectional survey of the ASPREE cohort.

Research square·2026
Same journal

Heavy-chain immune repertoire sequencing enables language-model prediction of antigen-specific antibodies.

Research square·2026
Same journal

25+ Years of TRPV4: From Discovery to Translational Horizons.

Research square·2026
See all related articles

We developed Scaled Gumbel Softmax (SGS) EchoNet, a data-efficient deep learning algorithm for echocardiograms. This new method improves robustness to noisy data without needing segmentation models.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Deep learning (DL) algorithms for transthoracic echocardiograms (TTEs) often require segmentation models.
  • These models can be data-intensive and sensitive to data quality issues.
  • Ventricular segmentation is a critical step in analyzing TTEs.

Purpose of the Study:

  • To present a data-efficient and robust deep learning algorithm for TTE analysis.
  • To eliminate the need for ventricular segmentation models in DL algorithms for TTEs.
  • To improve the handling of noisy inputs in TTE analysis.

Main Methods:

  • Developed a novel data-efficient deep learning algorithm named Scaled Gumbel Softmax (SGS) EchoNet.
  • Utilized an R(2+1)D convolutional encoder and transformed its output to estimate frame-level cardiac cycle weights.
Keywords:
Cardiac AssessmentClinical Decision SupportComputer VisionRobust Deep LearningUltrasounds

Related Experiment Videos

Last Updated: Jan 18, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
  • Obtained video representations for estimation without relying on segmentation models.

    • Main Results:

    • The SGS EchoNet algorithm demonstrates robustness to common data quality issues and noisy inputs.
    • The model achieves performance comparable to state-of-the-art methods.
    • The proposed transformation successfully obviates the need for a segmentation model.

    Conclusions:

    • The SGS EchoNet algorithm offers a data-efficient and robust alternative for TTE analysis using deep learning.
    • This approach enhances the reliability of DL models in the presence of noisy echocardiogram data.
    • The method shows promise for practical clinical applications requiring less data and improved noise tolerance.