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: Apr 22, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.7K

Personalized Deep Networks for Enhanced ECG Segmentation.

Maylon Pereira Folli1, Gabriel Tozatto Zago2, Stephanie Rezende Alvarenga Moulin Mares3

  • 1Electric Engineering Department, Federal Institute of Espírito Santo, Avenida Vitória, Vitória, 29040-780, Espírito Santo, Brazil.

Cardiovascular Engineering and Technology
|April 20, 2026
PubMed
Summary

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

Age and Sex Differences in Heart Rate Variability and Vagal Specific Patterns - Baependi Heart Study.

Global heart·2020
Same author

Diabetic retinopathy detection using red lesion localization and convolutional neural networks.

Computers in biology and medicine·2019
Same author

Retinal image quality assessment using deep learning.

Computers in biology and medicine·2018
Same author

Reference values for short-term resting-state heart rate variability in healthy adults: Results from the Brazilian Longitudinal Study of Adult Health-ELSA-Brasil study.

Psychophysiology·2018
Same author

Comparison between symbolic and spectral analyses of short-term heart rate variability in a subsample of the ELSA-Brasil study.

Physiological measurement·2015
Same author

[Medical assessments and measurements in ELSA-Brasil].

Revista de saude publica·2013
Same journal

A Trends Analysis and Scoping Review: Minimal Invasive Extracorporeal Circulation.

Cardiovascular engineering and technology·2026
Same journal

Auxetic Stents as a Next Generation Solution for Vascular Diseases-A Review.

Cardiovascular engineering and technology·2026
Same journal

Non-Invasive Evaluation of Pulmonary Artery Stenosis in Congenital Heart Disease Patients Using Phase Contrast MRI.

Cardiovascular engineering and technology·2026
Same journal

Impact of Tissue Freezing on the Functional and Biomechanical Characteristics of Porcine Aortic Roots.

Cardiovascular engineering and technology·2026
Same journal

Discriminating Breast Cancer Patients by Spectral Analysis of Arterial Pulse Waveforms.

Cardiovascular engineering and technology·2026
Same journal

Development of a Novel Holistic Assessment Strategy of TAVI-Induced Flow Restoration via Dimensionality Reduction Techniques.

Cardiovascular engineering and technology·2026
See all related articles
This summary is machine-generated.

Personalized deep learning models significantly improve electrocardiography (ECG) waveform segmentation by adapting to individual patient data. This approach enhances the accuracy of P-wave, QRS, and T-wave delineation for better cardiovascular diagnosis.

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Electrocardiography (ECG) is crucial for diagnosing heart conditions, with semantic segmentation aiming to precisely identify waveform boundaries.
  • Current deep learning models for ECG segmentation lack patient-specific adaptability and explainability, limiting their clinical utility.
  • Existing methods struggle with accurate delineation of complex waveforms like P and T waves.

Purpose of the Study:

  • To develop a personalized deep neural network for enhanced ECG semantic segmentation.
  • To improve the accuracy and generalizability of ECG waveform delineation by incorporating patient-specific variations.
  • To provide a more interpretable and clinically relevant basis for ECG analysis.

Main Methods:

Keywords:
Biomedical signal processingConvolutional neural networks (CNNs)Deep learningECG segmentationElectrocardiography (ECG)Long short-term memory (LSTM)Neural networksPatient-specific adaptationPersonalized healthcareQT database

Related Experiment Videos

Last Updated: Apr 22, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.7K
  • A deep neural network integrating Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks with an attention mechanism.
  • Introduction of a novel loss function to promote smoother temporal transitions and improved classification.
  • Model personalization through fine-tuning on individual patient data from the QT Database.

    • Main Results:

    • Substantial improvements in P-wave and QRS delineation accuracy.
    • Enhanced T-wave offset localization segmentation.
    • Demonstrated benefit of intra-patient adaptation for challenging waveform delineation, particularly P and T waves.

    Conclusions:

    • Personalized deep learning models significantly enhance ECG segmentation accuracy by capturing patient-specific morphology.
    • The proposed approach offers a stronger basis for clinically interpretable, waveform-level ECG analysis.
    • Intra-patient adaptation is key to improving the performance of deep learning models in ECG processing.