Enabling On-Device Model Personalization for Ventricular Arrhythmias Detection by Generative Adversarial Networks
Event Type
Research Manuscript
Virtual Programs
Hosted in Virtual Platform
Embedded System Design Methodologies
Embedded Systems
DescriptionImplantable Cardioverter Defibrillator (ICD) is an ultra-low-power device delivering in-time defibrillation on ventricular arrhythmias (VAs). The parameters of VAs detection mechanism on each recipient's ICD should be fine-tuned to achieve accurate detection. However, the process relies on the expertise and must be conducted manually by cardiologists. In this paper, we introduce a novel self-supervised on-device personalization of convolutional neural networks (CNNs) for VAs detection. We first propose a framework to enable on-device CNN update. Furthermore, we propose a generative model that learns to synthesize patient-specific intracardiac EGMs signals, which can be used as training data to improve patient-specific VAs detection.