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: Nov 28, 2025

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

568

Copula-Based Data Augmentation on a Deep Learning Architecture for Cardiac Sensor Fusion.

Diogo Silva, Steffen Leonhardt, Christoph Hoog Antink

    IEEE Journal of Biomedical and Health Informatics
    |November 25, 2020
    PubMed
    Summary

    Deep learning for clinical data now uses a novel synthesizer and multi-branch neural network. This approach enhances cardiac cycle detection and classification, even with limited or artifact-contaminated training data.

    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

    FEM-based volume estimation using electrode catheter measurements.

    Journal of electrical bioimpedance·2026
    Same author

    Decoding the Raf-Mek-Erk-Rsk pathway in prostate cancer: from molecular mechanisms to clinical opportunities.

    British journal of cancer·2026
    Same author

    For a better understanding of thermoregulation in premature infants≤28 weeks of gestation: infrared thermography (IRT) and photoplethysmography imaging (PPGI) in a hybrid camera model as non-contact measuring methods.

    Zeitschrift fur Geburtshilfe und Neonatologie·2026
    Same author

    A systematic review of pandemic ventilator designs.

    Biomedizinische Technik. Biomedical engineering·2026
    Same author

    Phase I trial of Ipatasertib plus Atezolizumab enhances PI3K/AKT pathway immune responses in solid tumors and refractory glioblastoma.

    Clinical cancer research : an official journal of the American Association for Cancer Research·2026
    Same author

    Spatial temperature monitoring of preterm infants using a multi-modal camera setup.

    Medical & biological engineering & computing·2026

    Area of Science:

    • Cardiology
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Traditional machine learning is integrated into clinical workflows.
    • Deep learning methods face challenges due to large data requirements and architecture adaptability.
    • Clinical adoption of deep learning is hindered by data needs and generalized model applications.

    Purpose of the Study:

    • To develop a cardiorespiratory signal synthesizer to address data scarcity.
    • To design a multi-branch convolutional neural network for optimal cardiac sensor fusion.
    • To improve deep learning model performance for cardiac cycle detection and classification.

    Main Methods:

    • A cardiorespiratory signal synthesizer was created using Gaussian copulas and Markov chains.
    • A multi-branch convolutional neural network architecture was developed for sensor fusion.

    Related Experiment Videos

    Last Updated: Nov 28, 2025

    Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
    05:32

    Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

    Published on: February 21, 2025

    568
  • Synthesizer-based data augmentation and Bayesian optimization were used for training.

    • Main Results:

    • The synthesizer generated realistic cardiorespiratory signals across domains and conditions.
    • The proposed network architecture surpassed previous models in performance.
    • Data augmentation significantly boosted performance in scenarios with limited, artifact-contaminated, or incomplete training data.

    Conclusions:

    • The developed methods effectively address data limitations in deep learning for clinical applications.
    • The novel approach enhances the feasibility of deep learning for cardiac analysis.
    • This work facilitates more robust and accurate cardiac cycle detection and classification.