Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Synthesizing Twelve-Lead Electrocardiograms from Two Asynchronous Leads

Yong-Yeon Jo, Young Sang Choi, Jong-Hwan Jang, Joon-Myoung Kwon

TL;DR

Experiments show classifiers trained on synthesized 12-lead electrocardiograms generated with ECGT2T outperforms models trained on one- or two-lead ECGs in detecting myocardial infarction and arrhythmia.

Abstract

The electrocardiogram (ECG) records electrical signals in a non-invasive way to observe the condition of the heart, typically looking at the heart from 12 different directions. Several types of the cardiac disease are diagnosed by using 12-lead ECGs Recently, various wearable devices have enabled immediate access to the ECG without the use of wieldy equipment. However, they only provide ECGs with a couple of leads. This results in an inaccurate diagnosis of cardiac disease due to lacking of required leads. We propose a deep generative model for ECG synthesis from two asynchronous leads to ten leads. It first represents a heart condition referring to two leads, and then generates ten leads based on the represented heart condition. Both the rhythm and amplitude of leads generated resemble those of the original ones, while the technique removes noise and the baseline wander appearing in the original leads. As a data augmentation method, our model improves the classification performance of models compared with models using ECGs with only one or two leads.

Towards Synthesizing Twelve-Lead Electrocardiograms from Two Asynchronous Leads

TL;DR

Experiments show classifiers trained on synthesized 12-lead electrocardiograms generated with ECGT2T outperforms models trained on one- or two-lead ECGs in detecting myocardial infarction and arrhythmia.

Abstract

The electrocardiogram (ECG) records electrical signals in a non-invasive way to observe the condition of the heart, typically looking at the heart from 12 different directions. Several types of the cardiac disease are diagnosed by using 12-lead ECGs Recently, various wearable devices have enabled immediate access to the ECG without the use of wieldy equipment. However, they only provide ECGs with a couple of leads. This results in an inaccurate diagnosis of cardiac disease due to lacking of required leads. We propose a deep generative model for ECG synthesis from two asynchronous leads to ten leads. It first represents a heart condition referring to two leads, and then generates ten leads based on the represented heart condition. Both the rhythm and amplitude of leads generated resemble those of the original ones, while the technique removes noise and the baseline wander appearing in the original leads. As a data augmentation method, our model improves the classification performance of models compared with models using ECGs with only one or two leads.

Paper Structure

This paper contains 8 sections, 5 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Proposed Architecture
  3. Objectives
  4. Training Procedure
  5. Data and Experiments
  6. Quality Assessment
  7. Classification Performance
  8. Conclusion

Figures (2)

  • Figure 1: ECGT2T model architecture. The model is comprised of style, mapping, generative, and discriminative networks. Each network is built with residual blocks. $L_{adv}$ is the adversarial objective, $L_{rec}$ is the reconstruction objective, $L_{con}$ is the lead consistency objective, and $L_{sty}$ is the style consistency objective.
  • Figure 2: 12-lead electrocardiogram samples over a two second window. For each subplot, the black line denotes the original signal while the blue and red lines represent the signals generated by ECGT2T, and ECGS2E respectively. ECGS2E takes in only Lead I as input and outputs 11 leads, while ECGT2T takes asynchronous Lead I and Lead II inputs and generates signals for 10 leads. Although ECGT2T uses two asynchronous leads, all leads are visualized synchronously for convenience.