Deep Learning Models for Denoising ECG Signals

Abstract

Effective and powerful methods for denoising real electrocardiogram (ECG) signals are important for wearable sensors and devices. Deep Learning (DL) models have been used extensively in image processing and other domains with great success but only very recently have been used in processing ECG signals. This paper presents several DL models namely Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Restricted Boltzmann Machine (RBM) together with the more conventional filtering methods (low pass filtering, high pass filtering, Notch filtering) and the standard wavelet-based technique for denoising EEG signals. These methods are trained, tested and evaluated on different synthetic and real ECG datasets taken from the MIT PhysioNet database and for different simulation conditions (i.e. various lengths of the ECG signals, single or multiple records). The resultsshow the CNN model is a performant model that can be used for off-line denoising ECG applications where it is satisfactory to train on a clean part of an ECG signal from an ECG record, and then to test on the same ECG signal, which would have some high level of noise added to it. However, for real-time applications or near-real time applications, this task becomes more cumbersome, as the clean part of an ECG signal is very probable to be very limited in size. Therefore the solution put forth in this work is to train a CNN model on 1 second ECG noisy artificial multiple heartbeat data (i.e. ECG at effort), which was generated in a first instance based on few sequences of real signal heartbeat ECG data (i.e. ECG at rest).Afterwards it would be possible to use the trained CNN model in real life situations to denoise the ECG signal. This corresponds also to reality, where usually the human is put at rest and the ECG is recorded and then the same human is asked to do some physical exercises and the ECG is recorded at effort. The quality of results is assessed visually but also by using the Root Mean Squared (RMS) and the Signal to Noise Ratio (SNR) measures. All CNN models used an NVIDIA TITAN V Graphical Processing Unit (GPU) with 12 GB RAM, which reduces drastically the computational times. Finally, as an element of novelty, the paper presents also a Design of Experiment (DoE) study which intends to determine the optimal structure of a CNN model, which type of study has not been seen in the literature before.

Band-Stop Smoothing Filter Design

“…In the literature, the deep learning (DL) method has been also used for signal denoising, e.g. for ECG denoising [50]- [52]. However, in these papers, even if results seem interesting at first glance, comparison with the best more classical methods are still missing.…”

Forecasting Nonlinear Systems with LSTM: Analysis and Comparison with EKF

“…In the case of signal filtering, the Arsene work [ 24 ] showed a performance comparison in electrocardiogram (ECG) signal filtering between two deep learning filters with the two most popular trends at present, convolutional neural networks (CNNs) and LSTM, versus wavelet filters. Finally, the CNN architecture achieved better performance than the LSTM and the wavelet filter, but the proposed LSTM architecture can be improved.…”

“…The general network architecture proposed in Llerena et al [ 19 ] consists of an encoder–decoder system based on good results with non-Markovian system models like [ 18 , 23 , 32 ]. Other fundamentals of design of this architecture focus on filtering problems, such as [ 24 ] or the identification of noisy systems [ 22 , 23 ]. The encoder and decoder are composed of LSTM recursive structures.…”

The Use of Time-Frequency Moments as Inputs of LSTM Network for ECG Signal Classification

“…Corneliu T. C. Arsene, R. Hankins, and H. Yin [37] applied a CNN regression model and LSTM network capable of rejecting very high levels of noise in the ECG signals. This is a situation that has not been addressed before.…”