A Cascaded Convolutional Neural Network for Assessing Signal Quality of Dynamic ECG.

Qifei Zhang,Lingjian Fu,Linyue Gu

doi:10.1155/2019/7095137

Abstract

Motion artifacts and myoelectrical noise are common issues complicating the collection and processing of dynamic electrocardiogram (ECG) signals. Recent signal quality studies have utilized a binary classification metric in which ECG samples are determined to either be clean or noisy. However, the clinical use of dynamic ECGs requires specific noise level classification for varying applications. Conventional signal processing methods, including waveform discrimination, are limited in their ability to remove motion artifacts and myoelectrical noise from dynamic ECGs. As such, a novel cascaded convolutional neural network (CNN) is proposed and demonstrated for application to the five-classification problem (low interference, mild motion artifacts, mild myoelectrical noise, severe motion artifacts, and severe myoelectrical noise). Specifically, this study finally categorizes dynamic ECG signals into three levels (low, mild, and severe) using the proposed CNN to meet clinical requirements. The network includes two components, the first of which was used to distinguish signal interference types, while the second was used to distinguish signal interference levels. This model does not require feature engineering, includes powerful nonlinear mapping capabilities, and is robust to varying noise types. Experimental data are composed of private dataset and public dataset, which were acquired from 90,000 four-second dynamic ECG signals and MIT-BIH Arrhythmia database, respectively. Experimental results produced an overall recognition rate of 92.7% on private dataset and 91.8% on public dataset. These results suggest the proposed technique to be a valuable new tool for dynamic ECG auxiliary diagnosis.

Highlights

Li et al [10] divided ECG signal quality into five levels according to signal-to-noise ratio (SNR)
Tests conducted on the MIT-BIH arrhythmia database produced an accuracy of 88.07% as well. While these studies could be applied to the classification of dynamic ECGs, an effective assessment of signal quality is required in clinical applications because dynamic signals often include motion artifacts and myoelectrical noise
We selected a segment with 4-second duration, based on two facts: after preprocessing, we found in a large number of clinical data that the possibility of two or more interference patterns coexisting within a 4-second period is extremely small and at least one cardiac rhythm cycle is included

Summary

Introduction

Signals containing mild and severe motion artifacts manifest as irregular abrupt waves with frequencies below 7 Hz. Myoelectrical noise, caused by muscle activity, is difficult to remove. Q S arrhythmia or myocardial ischemia, mild-interference signals could be confidently used for heartbeat or heart rate variability (HRV) measurements, and signals containing severe levels of interference could be safely ignored to prevent a false diagnosis. E study was focused on preventing the misidentification of motion artifacts or myoelectrical noise as arrhythmia in ICU ECG monitoring. Tests conducted on the MIT-BIH arrhythmia database produced an accuracy of 88.07% as well While these studies could be applied to the classification of dynamic ECGs, an effective assessment of signal quality is required in clinical applications because dynamic signals often include motion artifacts and myoelectrical noise

Objectives

Methods

Results