Ventricular Arrhythmia Classification Using Similarity Maps and Hierarchical Multi-Stream Deep Learning.

Objective: Ventricular arrhythmias are the primary arrhythmias that cause sudden cardiac death. We address the problem of classification between ventricular tachycardia (VT), ventricular fibrillation (VF) and non-ventricular rhythms (NVR).

Methods: To address the challenging problem of the discrimination between VT and VF, we develop similarity maps - a novel set of features designed to capture regularity within an ECG trace. These similarity maps are combined with features extracted through learnable Parzen band-pass filters and derivative features to discriminate between VT, VF, and NVR. To combine the benefits of these different features, we propose a hierarchical multi-stream ResNet34 architecture.

Results: Our empirical results demonstrate that the similarity maps significantly improve the accuracy of distinguishing between VT and VF. Overall, the proposed approach achieves an average class sensitivity of 89.68%, and individual class sensitivities of 81.46% for VT, 89.29% for VF, and 98.28% for NVR.

Conclusion: The proposed method achieves a high accuracy of ventricular arrhythmia detection and classification.

Significance: Correct detection and classification of ventricular fibrillation and ventricular tachycardia are essential for effective intervention and for the development of new therapies and translational medicine.