Multilevel Classification and Detection of Cardiac Arrhythmias With High-Resolution Superlet Transform and Deep Convolution Neural Network

Atrial fibrillation and ventricular fibrillation are the two most common cardiac arrhythmia. These cardiac arrhythmias cause heart strokes and other heart complications leading to an increased risk of heart failure. Early and accurate cardiac arrhythmia detection is vital to preventing various heart-related diseases. Electrocardiogram (ECG) is a popular and reliable method to detect cardiac arrhythmia and heart-related diseases. However, sometimes, it becomes difficult and time-consuming to interpret the ECG signal, even for a cardiac expert. This study proposes a deep learning-based method to effectively classify and detect cardiac arrhythmias (atrial fibrillation and ventricular fibrillation) using a time–frequency (TF) spectrogram of ECG records. The proposed framework utilizes superlet transform (SLT) to transform the 1-D ECG signal into a 2-D TF spectrogram. The last layer of the pretrained convolutional neural networks, namely, AlexNet, GoogLeNet, and DenseNet, is modified and then used to classify the ECG records into healthy heart, atrial fibrillation, and ventricular fibrillation. The proposed method is tested using ECG signals from the MIT-BIH arrhythmia database, the MIT-BIH malignant database, the Fantasia database, the AF termination challenge database, and the CU ventricular tachyarrhythmia database. The proposed method with DenseNet-201 architecture provides the best performance with an overall test accuracy of 96.2%. The proposed method reduces the system complexity as it does not require noise removal, handcrafted features, and beat detection. Furthermore, the proposed system automatically classifies the ECG signal into healthy heart, atrial fibrillation, and ventricular fibrillation.