Using the Redundant Convolutional Encoder–Decoder to Denoise QRS Complexes in ECG Signals Recorded with an Armband Wearable Device

Abstract

Long-term electrocardiogram (ECG) recordings while performing normal daily routines are often corrupted with motion artifacts, which in turn, can result in the incorrect calculation of heart rates. Heart rates are important clinical information, as they can be used for analysis of heart-rate variability and detection of cardiac arrhythmias. In this study, we present an algorithm for denoising ECG signals acquired with a wearable armband device. The armband was worn on the upper left arm by one male participant, and we simultaneously recorded three ECG channels for 24 h. We extracted 10-s sequences from armband recordings corrupted with added noise and motion artifacts. Denoising was performed using the redundant convolutional encoder–decoder (R-CED), a fully convolutional network. We measured the performance by detecting R-peaks in clean, noisy, and denoised sequences and by calculating signal quality indices: signal-to-noise ratio (SNR), ratio of power, and cross-correlation with respect to the clean sequences. The percent of correctly detected R-peaks in denoised sequences was higher than in sequences corrupted with either added noise (70–100% vs. 34–97%) or motion artifacts (91.86% vs. 61.16%). There was notable improvement in SNR values after denoising for signals with noise added (7–19 dB), and when sequences were corrupted with motion artifacts (0.39 dB). The ratio of power for noisy sequences was significantly lower when compared to both clean and denoised sequences. Similarly, cross-correlation between noisy and clean sequences was significantly lower than between denoised and clean sequences. Moreover, we tested our denoising algorithm on 60-s sequences extracted from recordings from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database and obtained improvement in SNR values of 7.08 ± 0.25 dB (mean ± standard deviation (sd)). These results from a diverse set of data suggest that the proposed denoising algorithm improves the quality of the signal and can potentially be applied to most ECG measurement devices.

A robust ECG denoising technique using variable frequency complex demodulation

“…Detected R peaks were visually inspected by three independent experts and the majority vote was taken as the correct decision. SNR improvement was calculated by subtracting the noisy signal SNR from the denoised signal SNR, as described in [23].…”

“…A multi-lead model-based ECG signal denoising with an adaptive guided filter is proposed in [22]. Finally, convolutional encoder-decoder approaches were proposed in [17], [23].…”

An Automated High-Accuracy Detection Scheme for Myocardial Ischemia Based on Multi-Lead Long-Interval ECG and Choi-Williams Time-Frequency Analysis Incorporating a Multi-Class SVM Classifier

“…Digital filters were used to remove the artifacts on the ECG, which affects the quality of the collected ECG, while a 0.5 Hz high-pass Finite Impulse Response (FIR) filter was used to remove the baseline wander shifting noise. Additionally, a bandpass FIR filter at a bandwidth of 2 Hz and 35 Hz centre frequency, was applied to eliminate muscle noise artifacts [ 26 , 27 , 28 ]. The ECG raw data were then scaled to eliminate dynamic interim changes in the ECG signal, stemming from human physiological subjects and activities.…”

Inter-Beat Interval Estimation with Tiramisu Model: A Novel Approach with Reduced Error

“…Juho et al, on the other hand, utilized a bidirectional Long-Short Term Memory (LSTM) network to suppress the noise up to 0.1dB and detect peaks from it [34]. A CNN encoder-decoder is used by Natasa et al to denoise the QRS complexes of the long term ECG signals acquired with their wearable armband device and used them later to calculate HR [35]. They too were able to use the denoising process up to -17dB with inclusion of white and brown noise, but no muscle artifact.…”