Noise Rejection for Wearable ECGs Using Modified Frequency Slice Wavelet Transform and Convolutional Neural Networks

Progress in wearable techniques makes the long-term daily electrocardiogram (ECG) monitoring possible. However, the long-term wearable ECGs can be significantly contaminated by various noises, which affect the detection and diagnosis of cardiovascular diseases (CVDs). The situation becomes more serious for wearable ECG screening, where the data are huge, and doctors have no way to visually check the signal quality episode-by-episode. Therefore, automatic and accurate noise rejection for the wearable big-data ECGs is craving. This paper addressed this issue and proposed a noise rejection method for wearable ECGs based on the combination of modified frequency slice wavelet transform (MFSWT) and convolutional neural network (CNN). Wearable ECGs were recorded using the newly developed 12-lead Lenovo smart ECG vest with a sample rate of 500 Hz and a resolution of 16 bit. One thousand 10-s ECG segments were picked up and were manually labeled into three quality types: clinically useful segments with good signal quality (type A), clinically useful segments with poor signal quality (type B), and clinically useless segments (pure noises, type C). Each of the 1,000 10-s ECG segments were transformed into a 2-D time-frequency (T-F) image using the MFSWT, with a pixel size of $200\times 50$ . Then, the 2-D grayscale images from MFSWT were fed into a 13-layer CNN model for training the classification models. Results from the standard 5-folder cross-validation showed that the proposed combination method of MFSWT and CNN achieved a highest classification accuracy of 86.3%, which was higher than the comparable methods from continuous wavelet transform (CWT) and artificial neural networks (ANN). The combination of MFSWT and CNN also had a good calculation efficiency. This paper indicated that the combination of MFSWT and CNN is a potential method for automatic identification of noisy segments from wearable ECG recordings.

[1]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[2]  Luca Maria Gambardella,et al.  Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Flexible, High Performance Convolutional Neural Networks for Image Classification , 2022 .

[3]  G D Clifford,et al.  Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms , 2012, Physiological measurement.

[4]  Xiangyu Zhang,et al.  Signal Quality Assessment and Lightweight QRS Detection for Wearable ECG SmartVest System , 2019, IEEE Internet of Things Journal.

[5]  Zhonghong Yan,et al.  Frequency slice wavelet transform for transient vibration response analysis , 2009 .

[6]  Feng Wu,et al.  Background Prior-Based Salient Object Detection via Deep Reconstruction Residual , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8]  Jun Dong,et al.  Deep learning research on clinical electrocardiogram analysis , 2015 .

[9]  S. Barold.  Willem Einthoven and the birth of clinical electrocardiography a hundred years ago. , 2003, Cardiac electrophysiology review.

[10]  Wang Li.  The Advance Research and Analysis of Electrocardiogram Pattern Classification , 2010 .

[11]  Ikaro Silva,et al.  Improving the quality of ECGs collected using mobile phones: The PhysioNet/Computing in Cardiology Challenge 2011 , 2011, 2011 Computing in Cardiology.

[12]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[13]  R G Mark,et al.  Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter , 2008, Physiological measurement.

[14]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[15]  Shoushui Wei,et al.  ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix , 2014, Journal of Zhejiang University SCIENCE C.

[16]  Pablo Laguna,et al.  Characterization of Dynamic Interactions Between Cardiovascular Signals by Time-Frequency Coherence , 2012, IEEE Transactions on Biomedical Engineering.

[17]  Zhongwei Jiang,et al.  An overall theoretical description of frequency slice wavelet transform , 2010 .

[18]  Deyu Meng,et al.  Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Junwei Han,et al.  Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  R. Ghongade,et al.  A robust and reliable ECG pattern classification using QRS morphological features and ANN , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[21]  Lei Guo,et al.  Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Udit Satija,et al.  Real-Time Signal Quality-Aware ECG Telemetry System for IoT-Based Health Care Monitoring , 2017, IEEE Internet of Things Journal.

[23]  Gari D Clifford,et al.  Multimodal heart beat detection using signal quality indices , 2015, Physiological measurement.

[24]  Peng Li,et al.  Real-time signal quality assessment for ECGs collected using mobile phones , 2011, 2011 Computing in Cardiology.

[25]  Zhonghong Yan,et al.  Frequency slice algorithm for modal signal separation and damping identification , 2011 .

[26]  Xuelong Li,et al.  Detection of Co-salient Objects by Looking Deep and Wide , 2016, International Journal of Computer Vision.

[27]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[28]  Hongxun Yao,et al.  Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models , 2017, International Conference on Digital Image Processing.

[29]  Lotfi Nabli,et al.  ECG waves determining using multiscaled CWT , 2013, 2013 International Conference on Control, Decision and Information Technologies (CoDIT).

[30]  Jianqing Li,et al.  Patient-Specific Deep Architectural Model for ECG Classification , 2017, Journal of healthcare engineering.

[31]  David E. Bloom,et al.  From Burden to "Best Buys": Reducing the Economic Impact of Non-Communicable Disease in Low- and Middle-Income Countries , 2011 .

[32]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .