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: Sep 12, 2025

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
06:07

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

3.9K

A method for ECG denoising based on generative adversarial networks.

Enhan Liu1, Zhengqian Jiang1, Zihang Wang2

  • 1College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China.

International Journal of Medical Informatics
|August 6, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Masking and Demasking Agents01:19

Masking and Demasking Agents

2.7K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A teacher-student deep learning framework for enhanced clinical screening of heart failure from 12-lead electrocardiograms.

Physiological measurement·2026
Same author

Precise Structural Analysis of Neutral Glycans Using Aerolysin Mutant T240R Nanopore.

ACS nano·2024
Same author

Thienopyrimidine-derived multifunctional fluorescence sensor for the detection of Cu<sup>2+</sup>, Fe<sup>3+</sup>, and PPi in different solvents.

Luminescence : the journal of biological and chemical luminescence·2024
Same author

Label-free cell phenotypic profiling of histamine H4R receptor and discovery of non-competitive H4R antagonist from natural products.

Bioorganic chemistry·2024
Same author

Engineering the passivation routes of perovskite films towards high performance solar cells.

Chemical science·2024
Same author

Multiscale apple recognition method based on improved CenterNet.

Heliyon·2024
Same journal

BlockFedMed: A blockchain-federated learning framework for privacy-preserving mortality prediction across heterogeneous intensive care units.

International journal of medical informatics·2026
Same journal

Integrating clinical decision support systems in pediatric oncology: A scoping review of applications, implementation gaps, and management Implications.

International journal of medical informatics·2026
Same journal

Understanding digital health capability of allied health professionals - a mixed-methods study with content validity analysis.

International journal of medical informatics·2026
Same journal

On-premises open-source large language models for privacy-preserving multimodal depression screening.

International journal of medical informatics·2026
Same journal

Data mining methods, tasks, and algorithms for adverse drug reaction analysis in pharmacovigilance: A scoping review.

International journal of medical informatics·2026
Same journal

Development and validation of an interpretable machine learning model for predicting systemic inflammatory response syndrome after percutaneous nephrolithotomy: A multicenter study.

International journal of medical informatics·2026
See all related articles

This study introduces a Generative Adversarial Network (GAN) approach for denoising grayscale electrocardiograms (ECGs) from paper records. The method effectively recovers accurate waveforms and improves heart disease diagnostic accuracy.

Area of Science:

  • Biomedical Signal Processing
  • Artificial Intelligence in Healthcare
  • Medical Imaging Analysis

Background:

  • Grayscale electrocardiograms (ECGs) transcribed from paper records often suffer from significant noise.
  • This noise complicates accurate waveform interpretation and impacts downstream diagnostic tasks.
  • Existing denoising methods may not sufficiently address the unique noise characteristics of transcribed ECGs.

Purpose of the Study:

  • To develop a robust Generative Adversarial Network (GAN)-based framework for denoising grayscale ECGs.
  • To create an effective method for constructing a high-quality denoising dataset for ECGs.
  • To improve the accuracy of ECG waveform recovery and subsequent heart disease diagnosis.

Main Methods:

  • A GANs-based ECG waveform denoising approach (Generative Adversarial Network Electrocardiogram Denoising) was proposed, training a generator and discriminator simultaneously for end-to-end denoising.
Keywords:
ECG DenoisingECG processingGenerative adversarial networkImage segmentation

Related Experiment Videos

Last Updated: Sep 12, 2025

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
06:07

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

3.9K
  • An ECG Background Noise Generation technique using GANs was developed to create diverse, realistic noise patterns for dataset construction.
  • The denoising performance was evaluated using waveform similarity metrics and impact on heart disease diagnostic accuracy.

    • Main Results:

    • The proposed GANs-based method achieved superior performance in ECG denoising, with a Dice Similarity Coefficient of 92.72% and IoU of 86.58%.
    • The denoised dataset significantly improved heart disease diagnostic accuracy, achieving 89% and 82.19% accuracy, outperforming baseline methods.
    • The framework demonstrated effective end-to-end waveform recovery and enhanced diagnostic utility.

    Conclusions:

    • A novel GANs-based framework for ECG denoising dataset construction and an end-to-end denoising model were successfully developed.
    • The joint application of the proposed dataset generation and denoising methods effectively addresses the challenge of noisy ECGs.
    • This approach offers a promising solution for accurate ECG waveform recovery from degraded paper records.