Related Experiment Video
Updated: Jan 26, 2026
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
Ventricular ectopic beat detection using a wavelet transform and a convolutional neural network
Qichen Li1,2, Chengyu Liu3, Qiao Li2
1Department of Engineering Science, University of Oxford, Oxford, United Kingdom.
Insights
This study introduces a novel wavelet transform and deep learning method for accurately identifying ventricular ectopic beats (VEBs) in ECG data. The approach demonstrates high accuracy and excellent generalization across different datasets, improving cardiac arrhythmia detection.
Area of Science:
- Cardiology
- Biomedical Engineering
- Artificial Intelligence in Medicine
Background:
- Ventricular ectopic beats (VEBs) disrupt normal cardiac function and heart rate variability analysis.
- VEBs can be misidentified as artifacts due to similar morphology and timing.
- Accurate VEB detection is crucial for identifying potentially life-threatening cardiac conditions.
Purpose of the Study:
- To develop and evaluate a method for automated classification of ventricular ectopic beats (VEBs).
- To utilize wavelet transform and deep learning for enhanced VEB identification.
- To assess the method's performance on independent cardiac arrhythmia databases.
Main Methods:
- Electrocardiogram (ECG) segments were transformed into 2D time-frequency images using three wavelet types (Morlet, Paul, Gaussian derivative).
- A convolutional neural network (CNN) was employed to classify these images, optimizing filters for accuracy.
- The model was validated using ten-fold cross-validation on the MIT-BIH arrhythmia database and tested on the AHA database.
Main Results:
- The proposed algorithm, particularly with the Paul wavelet, achieved an 84.94% F1 score and 97.96% accuracy on the MIT-BIH dataset.
- Independent testing on the AHA database yielded an 84.96% F1 score and 97.36% accuracy.
- The results demonstrate robust performance and effective discrimination of VEBs from other cardiac beats and artifacts.
Conclusions:
- The combination of wavelet transform and CNN provides an effective automated method for VEB classification.
- The developed network exhibits strong generalization capabilities, performing well across different datasets.
- This approach offers a significant advancement in the accurate and reliable detection of ventricular ectopic beats.
Objective:
Ventricular contractions in healthy individuals normally follow the contractions of atria to facilitate more efficient pump action and cardiac output. With a ventricular ectopic beat (VEB), volume within the ventricles are pumped to the body's vessels before receiving blood from atria, thus causing inefficient blood circulation. VEBs tend to cause perturbations in the instantaneous heart rate time series, making the analysis of heart rate variability inappropriate around such events, or requiring special treatment (such as signal averaging). Moreover, VEB frequency can be indicative of life-threatening problems. However, VEBs can often mimic artifacts both in morphology and timing. Identification of VEBs is therefore an important unsolved problem. The aim of this study is to introduce a method of wavelet transform in combination with deep learning network for the classification of VEBs.
Approach:
We proposed a method to automatically discriminate VEB beats from other beats and artifacts with the use of wavelet transform of the electrocardiogram (ECG) and a convolutional neural network (CNN). Three types of wavelets (Morlet wavelet, Paul wavelet and Gaussian derivative) were used to transform segments of single-channel (1D) ECG waveforms to two-dimensional (2D) time-frequency 'images'. The 2D time-frequency images were then passed into a CNN to optimize the convolutional filters and classification. Ten-fold cross validation was used to evaluate the approach on the MIT-BIH arrhythmia database (MIT-BIH). The American Heart Association (AHA) database was then used as an independent dataset to evaluate the trained network.
Main Results:
Ten-fold cross validation results on MIT-BIH showed that the proposed algorithm with Paul wavelet achieved an overall F1 score of 84.94% and accuracy of 97.96% on out of sample validation. Independent test on AHA resulted in an F1 score of 84.96% and accuracy of 97.36%.
Significance:
The trained network possessed exceptional transferability across databases and generalization to unseen data.
Related Concept Videos
01:09Beats
01:17Convolution Properties II
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
01:20Convolution Properties I
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
01:33Bacterial Transformation
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
02:26Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
02:18Network Covalent Solids
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...