Sequential Factorized Autoencoder for Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms

• Published in: IEEE transactions on biomedical engineering Vol. 67; no. 5; pp. 1505 - 1516
• Main Authors: Gyawali, Prashnna Kumar, Horacek, B. Milan, Sapp, John L., Wang, Linwei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Classification; Data models; Disentangled Representations; EKG; Electrocardiography; Electrophysiology; Heart; Logic gates; Long short-term memory; Mapping; Performance enhancement; Recurrent neural networks; Sequential Autoencoder; Tachycardia; Variation; Ventricle; Ventricular Tachycardia

Objective: This work presents a novel approach to handle the inter-subject variations existing in the population analysis of ECG, applied for localizing the origin of ventricular tachycardia (VT) from 12-lead electrocardiograms (ECGs). Methods: The presented method involves a factor disentangling se...