Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks

Mohamed F Tolba,Abdelrahman M Shaker,Howida A Shedeed,Manal Tantawi

doi:10.1109/access.2020.2974712

Mohamed F Tolba, Abdelrahman M Shaker + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2974712

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 163	License type: CC BY 4.0

Affiliation: Ain Shams University

Abstract

Electrocardiograms (ECGs) play a vital role in the clinical diagnosis of heart diseases. An ECG record of the heart signal over time can be used to discover numerous arrhythmias. Our work is based on 15 different classes from the MIT-BIH arrhythmia dataset. But the MIT-BIH dataset is strongly imbalanced, which impairs the accuracy of deep learning models. We propose a novel data-augmentation technique using generative adversarial networks (GANs) to restore the balance of the dataset. Two deep learning approaches-an end-to-end approach and a two-stage hierarchical approach-based on deep convolutional neural networks (CNNs) are used to eliminate hand-engineering features by combining feature extraction, feature reduction, and classification into a single learning method. Results show that augmenting the original imbalanced dataset with generated heartbeats by using the proposed techniques more effectively improves the performance of ECG classification than using the same techniques trained only with the original dataset. Furthermore, we demonstrate that augmenting the heartbeats using GANs outperforms other common data augmentation techniques. Our experiments with these techniques achieved overall accuracy above 98.0%, precision above 90.0%, specificity above 97.4%, and sensitivity above 97.7% after the dataset had been balanced using GANs, results that outperform several other ECG classification methods.

Highlights

An ECG is a standard tool for measuring the electrical activity of the heart and for diagnosing cardiac arrhythmias
We propose a novel data augmentation technique based on the combination of real and synthetic heartbeats using generative adversarial networks (GANs) to improve the classification of ECG heartbeats of 15 different classes from the MIT-BIH arrhythmia dataset
CLASSIFICATION STAGE We propose two approaches based on deep convolutional neural networks (CNNs) to classify 15 arrhythmias from the MIT-BIH dataset that are distinct from other recent classification approaches; no significant feature extraction of ECG data is needed to achieve strong classification performance

Summary

Introduction

An ECG is a standard tool for measuring the electrical activity of the heart and for diagnosing cardiac arrhythmias. Using an ECG involves placing electrodes on the surface of the body—such as the chest, neck, and arms—in order to detect electrical changes in the heart. The P wave shows atrial contractions; the QRS complex shows ventricular contractions; the T wave shows the electrical activity produced as the ventricles are recharged for the contraction [1]. Study of these complex waves and the cardiac activities they represent is vital for diagnosis of various arrhythmias [2]. It is difficult for a cardiologist to correctly analyze a large number of ECG records given their complexity and the amount of time required to analyze them [3]

Methods

Results

Conclusion