Synthetic Electrogram Generation with Variational Autoencoders for ECGI

TL;DR

This paper explores variational autoencoders to generate synthetic atrial electrograms, addressing data scarcity in ECGI and improving deep learning-based intracardiac electrogram estimation.

Contribution

It introduces two VAE models for rhythm-specific and class-conditioned EGM generation, demonstrating their utility for data augmentation in ECGI.

Findings

VAE-S achieves high fidelity with in silico EGMs

VAE-C enables rhythm-specific EGM generation

Data augmentation with generated EGMs improves EGM reconstruction performance

Abstract

Atrial fibrillation (AF) is the most prevalent sustained cardiac arrhythmia, and its clinical assessment requires accurate characterization of atrial electrical activity. Noninvasive electrocardiographic imaging (ECGI) combined with deep learning (DL) approaches for estimating intracardiac electrograms (EGMs) from body surface potentials (BSPMs) has shown promise, but progress is hindered by the limited availability of paired BSPM-EGM datasets. To address this limitation, we investigate variational autoencoders (VAEs) for the generation of synthetic multichannel atrial EGMs. Two models are proposed: a sinus rhythm-specific VAE (VAE-S) and a class-conditioned VAE (VAE-C) trained on both sinus rhythm and AF signals. Generated EGMs are evaluated using morphological, spectral, and distributional similarity metrics. VAE-S achieves higher fidelity with respect to in silico EGMs, while VAE-C enables rhythm-specific generation at the expense of reduced sinus reconstruction quality. As a proof of concept, the generated EGMs are used for data augmentation in a downstream noninvasive EGM reconstruction task, where moderate augmentation improves estimation performance. These results demonstrate the potential of VAE-based generative modeling to alleviate data scarcity and enhance deep learning-based ECGI pipelines.