Related Experiment Video
Updated: Jan 14, 2026
Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
Published on: April 11, 2025
Classification of cardiac electrical signals between patients with myocardial infarction and healthy controls by
Muqing Deng1,2, Boyan Li2, Mingying Ma2
1Center of Preventive Disease, The People's Hospital of Yangjiang, Yangjiang, People's Republic of China.
Insights
This study introduces an automated method for detecting myocardial infarction (MI) using electrocardiogram (ECG) time-frequency features and 3D deep learning. The approach achieves high accuracy in classifying MI from ECG signals, aiding faster diagnosis.
Area of Science:
- Cardiology
- Artificial Intelligence
- Biomedical Signal Processing
Background:
- Electrocardiogram (ECG) signal classification is crucial for myocardial infarction (MI) detection.
- Current ECG interpretation is time-consuming and requires expert cardiologists.
Purpose of the Study:
- To develop an automated MI detection method using cardiac time-frequency features and 3D convolutional neural networks (C3D).
- To improve the efficiency and accuracy of MI screening.
Main Methods:
- ECG feature representation using time-frequency spectrograms.
- Application of a novel 3D convolutional neural network (C3D) for deep feature learning.
- Utilizing all twelve ECG leads for comprehensive cardiac characteristic analysis.
Main Results:
- Achieved classification accuracies of 94.20% (2-fold), 96.20% (5-fold), and 97.32% (10-fold) on the PTB database.
- The method effectively captures dynamical characteristics of time-varying ECG signals.
- Demonstrated high performance in two-class classification (MI vs. Healthy Control).
Conclusions:
- The proposed automated method based on time-frequency features and 3D C3D networks offers a promising approach for MI detection.
- This technique can reduce diagnostic time and reliance on expert interpretation.
- The method shows significant potential for clinical application in MI screening.
Abstract:
Electrocardiogram (ECG) signal classification plays an important role in myocardial infarction (MI) detection and screening. Despite that much progress has been made, the interpretation of ECG signals is still extremely time-consuming, and heavily relies expertise of clinical cardiologists. In this paper, an automated classification method is developed based on cardiac time-frequency features and 3D convolutional neural networks for MI detection. First, an ECG feature representation scheme based on time-frequency spectrograms without complicated signal segmentation and morphological analysis, is proposed to elaborate the dynamical characteristics underlying time-varying ECG signals. Second, a new 3D convolutional neural networks (C3D) is adopted for in-depth feature learning underlying the extracted time-frequency features. The proposed 3D deep network can take advantage of the encoded spatial characteristics extracted from convolutional neural network and the full use of cardiac characteristics underlying all twelve leads. For the goal of two-class classification (MI or HC), a classification accuracy of 94.20%, 96.20% and 97.32% are achieved on the public PTB database under two-fold, five-fold and ten-fold cross-validation, respectively.
