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 26, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732

Data Augmentation-Enhanced Myocardial Infarction Classification and Localization Using a ResNet-Transformer Cascaded

Yunfan Chen1, Qi Gao1, Jinxing Ye1

  • 1Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, Hubei University of Technology, Wuhan 430068, China.

Biology
|October 29, 2025
PubMed
Summary

Related Concept Videos

Heart Failure IV: Classification and Diagnostic Evaluation01:30

Heart Failure IV: Classification and Diagnostic Evaluation

861
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
861

You might also read

Related Articles

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

Sort by
Same author

TFDF: Self-Supervised Time-Frequency Dynamic Fusion with Dual Constraints for Atrial Fibrillation Detection.

IEEE journal of biomedical and health informatics·2026
Same author

Multiscale Feature Enhancement and Bidirectional Temporal Dependency Networks for Arrhythmia Classification.

Biology·2026
Same author

A Multi-Domain Feature Fusion CNN for Myocardial Infarction Detection and Localization.

Biosensors·2025
Same author

Spatial Blind Source Estimation of Respiratory Rate and Heart Rate Detection Based on Frequency-Modulated Continuous Wave Radar.

Sensors (Basel, Switzerland)·2025
Same author

Automated arrhythmia classification based on a pyramid dense connectivity layer and BiLSTM.

Technology and health care : official journal of the European Society for Engineering and Medicine·2025
Same author

A novel atrial fibrillation automatic detection algorithm based on ensemble learning and multi-feature discrimination.

Medical & biological engineering & computing·2024
Same journal

Spatial Heterogeneity of Phytoplankton Taxa and Functional Groups Under Multidimensional Environmental Factors in Karst Urban Rivers.

Biology·2026
Same journal

Paleopathology of a Lower Miocene Carettochelyid Turtle from the Moghra Formation, Egypt.

Biology·2026
Same journal

Effects of Type I Diabetes Mellitus and Masticatory Loading on Mandibular Growth in Growing Rats: A Longitudinal CBCT Study.

Biology·2026
Same journal

Data-Limited Stock Status Assessment of Bonga Shad, <i>Ethmalosa fimbriata</i> (Bowdich, 1825) and Lesser African Threadfin, <i>Galeoides decadactylus</i> (Bloch, 1795) in the Central Gulf of Guinea.

Biology·2026
Same journal

Gonadogenesis in the Bearded Dragon (<i>Pogona vitticeps</i>, Agamidae): A Comprehensive Histological Analysis from Gonadal Ridge Formation to Testicular and Ovarian Development.

Biology·2026
Same journal

The Programmable Microbiome: Integrative AI and Multi-Omics Frameworks for Precision T2DM Management.

Biology·2026
See all related articles
This summary is machine-generated.

This study introduces a ResNet-Transformer cascaded network (RTCN) for improved myocardial infarction (MI) diagnosis using electrocardiogram (ECG) signals. The novel method enhances accuracy by better utilizing dynamic cardiac information and addressing data imbalance.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Signal Processing

Background:

  • Accurate myocardial infarction (MI) diagnosis is crucial for public health.
  • Traditional manual feature extraction in ECG analysis is limited.
  • Existing deep learning models struggle with dynamic cardiac information, global/local feature capture, and data imbalance.

Purpose of the Study:

  • To propose a novel deep learning model for enhanced ECG-based MI diagnosis.
  • To improve the utilization of dynamic information and capture both global and local ECG features.
  • To address data imbalance issues in ECG datasets for more robust classification.

Main Methods:

  • Utilized S-transform to extract global time-frequency features from ECG signals, capturing dynamic cardiac cycle changes.
Keywords:
ECGS-transformdata augmentationmyocardial infarction

Related Experiment Videos

Last Updated: Apr 26, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732
  • Developed a ResNet-Transformer cascaded network (RTCN) to collaboratively extract multi-scale local features and global temporal dependencies.
  • Employed the Denoising Diffusion Probabilistic Model (DDPM) for data augmentation of minority ECG classes.

    • Main Results:

    • The RTCN model demonstrated improved processing of time-frequency ECG features.
    • Data augmentation using DDPM increased inter-patient accuracy for minority classes from 61.66% to 68.39%.
    • Gradient-weighted Class Activation Mapping (Grad-CAM) confirmed the model's attention aligns with pathological ECG features, indicating clinical interpretability.

    Conclusions:

    • The proposed RTCN model effectively addresses limitations in current deep learning approaches for ECG analysis.
    • The integration of S-transform, ResNet-Transformer architecture, and DDPM significantly enhances MI diagnostic accuracy and robustness.
    • The model exhibits strong clinical interpretability, paving the way for advanced AI-driven cardiovascular diagnostics.