Phase mapping for cardiac unipolar electrograms with neural network instead of phase transformation

TL;DR

This paper introduces a neural network-based phase-like transformation (PLT) for cardiac electrogram analysis, replacing traditional phase mapping with a learned approach that enhances robustness and visualization of complex cardiac signals.

Contribution

The study proposes a novel neural network-based PLT for phase mapping, improving upon traditional phase transformation methods in cardiac electrogram analysis.

Findings

PLT effectively visualizes complex cardiac activity.

The approach demonstrates robustness on personalized human torso models.

Neural network-based PLT outperforms traditional phase transformation.

Abstract

A phase mapping is an approach to processing signals of electrograms recorded from the surface of cardiac tissue. The main concept of phase mapping is the application of the phase transformation with the aim to obtain signals with useful properties. In our study, we propose to use a simple sawtooth signal instead of a phase signal for processing of electrogram data and building of the phase maps. We denote transformation that can provide this signal as a phase-like transformation (PLT). PLT defined via a convolutional neural network that is trained on a dataset from computer models of cardiac tissue electrophysiology. The proposed approaches were validated on data from the detailed personalized model of the human torso electrophysiology. This paper includes visualization of the phase map based on PLT and shows the robustness of the proposed approaches in the analysis of the complex non-stationary periodic activity of the excitable cardiac tissue.