Efficient Extraction of Deep Image Features Using a Convolutional Neural Network (CNN) for Detecting Ventricular Fibrillation and Tachycardia

Abstract

To safely select the proper therapy for ventricular fibrillation (VF), it is essential to distinguish it correctly from ventricular tachycardia (VT) and other rhythms. Provided that the required therapy is not the same, an erroneous detection might lead to serious injuries to the patient or even cause ventricular fibrillation (VF). The primary innovation of this study lies in employing a CNN to create new features. These features exhibit the capacity and precision to detect and classify cardiac arrhythmias, including VF and VT. The electrocardiographic (ECG) signals utilized for this assessment were sourced from the established MIT-BIH and AHA databases. The input data to be classified are time–frequency (tf) representation images, specifically, Pseudo Wigner–Ville (PWV). Previous to Pseudo Wigner–Ville (PWV) calculation, preprocessing for denoising, signal alignment, and segmentation is necessary. In order to check the validity of the method independently of the classifier, four different CNNs are used: InceptionV3, MobilNet, VGGNet and AlexNet. The classification results reveal the following values: for VF detection, there is a sensitivity (Sens) of 98.16%, a specificity (Spe) of 99.07%, and an accuracy (Acc) of 98.91%; for ventricular tachycardia (VT), the sensitivity is 90.45%, the specificity is 99.73%, and the accuracy is 99.09%; for normal sinus rhythms, sensitivity stands at 99.34%, specificity is 98.35%, and accuracy is 98.89%; finally, for other rhythms, the sensitivity is 96.98%, the specificity is 99.68%, and the accuracy is 99.11%. Furthermore, distinguishing between shockable (VF/VT) and non-shockable rhythms yielded a sensitivity of 99.23%, a specificity of 99.74%, and an accuracy of 99.61%. The results show that using tf representations as a form of image, combined in this case with a CNN classifier, raises the classification performance above the results in previous works. Considering that these results were achieved without the preselection of ECG episodes, it can be concluded that these features may be successfully introduced in Automated External Defibrillation (AED) and Implantable Cardioverter Defibrillation (ICD) therapies, also opening the door to their use in other ECG rhythm detection applications.

An Arrhythmia classification approach via deep learning using single-lead ECG without QRS wave detection

“…When comparing our proposed model with state-of-the-art models validated in the same public dataset, it is important to note that few CNN studies have reported using single lead to identify multiple types of arrhythmias, regardless of whether they utilized open datasets. However, there are some similar experiments, such as those focusing on using single-lead ECG to detect AFIB [ 27 ] and using CNN to detect VT and VF [ 28 ]. Yun et al utilized 11 open-source databases from PhysioNet and developed a deep learning model based on transformer for AFIB/AFL segmentation in single lead ECG using self-supervised learning with masked signal modeling [ 27 ].…”

“…A. Mjahad et al . used MIT-BIH and AHA databases and employed four different CNN architectures (InceptionV3, MobileNet, VGGNet, and AlexNet) to discern VF and VT features [ 28 ]. The results showed a sensitivity of 98.16% and specificity of 99.07% for VF, sensitivity of 90.45% and specificity of 99.73% for VT, sensitivity of 99.34% and specificity of 98.35% for NSR, and sensitivity of 96.98% and specificity of 99.68% for other rhythms, with corresponding accuracies.…”