Investigating Deep Convolution Conditional GANs for Electrocardiogram Generation

Cardiac arrhythmia is the leading cause of death worldwide that occurs due to irregular heartbeats obtained using an electrocardiogram (ECG) signal. The occurrence of irregular beats among the normal beats is very rare thereby creating the problem of data imbalance. This paper proposes a deep convolution conditional generative adversarial network model for ECG generation that owns the imbalanced distribution among different beat classes, namely normal, supraventricular ectopic beats, ventricular ectopic beats, and fusion beats as recommended by the Association for the Advancement of Medical Instrumentation (AAMI). Convolution neural network based generator and discriminator models are investigated that incorporates the class label information in addition to the conventional input for effective generation of minority class of beats. Different loss functions and noise distributions have been individually explored for obtaining an effective model. Moreover, the model convergence was improved with the introduction of the parameter twist that allows the gradient to backpropagate at a faster pace during early stages of training. The effectiveness of the model was tested on a standard benchmark MIT-BIH dataset and the quality of generated signals was measured using seven quantitative measures.

[1]  Moncef Gabbouj,et al.  Personalized Monitoring and Advance Warning System for Cardiac Arrhythmias , 2017, Scientific Reports.

[2]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[3]  Zhi-Dong Zhao,et al.  A New Method for Removal of Baseline Wander and Power Line Interference in ECG Signals , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[4]  Kira Radinsky,et al.  PGANs: Personalized Generative Adversarial Networks for ECG Synthesis to Improve Patient-Specific Deep ECG Classification , 2019, AAAI.

[5]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[6]  John T. Guibas,et al.  Synthetic Medical Images from Dual Generative Adversarial Networks , 2017, ArXiv.

[7]  Seiichi Uchida,et al.  Biosignal Data Augmentation Based on Generative Adversarial Networks , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[8]  Philip de Chazal,et al.  A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[9]  Evgueni A. Haroutunian,et al.  Information Theory and Statistics , 2011, International Encyclopedia of Statistical Science.

[10]  Ruqiang Yan,et al.  ECG Arrhythmias Detection Using Auxiliary Classifier Generative Adversarial Network and Residual Network , 2019, IEEE Access.

[11]  Pierre-François Marteau,et al.  Time Warp Edit Distance with Stiffness Adjustment for Time Series Matching , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Tomas E. Ward,et al.  Quick and Easy Time Series Generation with Established Image-based GANs , 2019, ArXiv.

[14]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[15]  Philip Chan,et al.  Toward accurate dynamic time warping in linear time and space , 2007, Intell. Data Anal..

[16]  Tomas E. Ward,et al.  Synthesis of Realistic ECG using Generative Adversarial Networks , 2019, ArXiv.

[17]  B. V. K. Vijaya Kumar,et al.  Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals , 2012, IEEE Transactions on Biomedical Engineering.

[18]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[19]  Quan Liu,et al.  Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network , 2019, Scientific Reports.

[20]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[21]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[22]  Miguel C. Soriano,et al.  Electrocardiogram Classification Using Reservoir Computing With Logistic Regression , 2015, IEEE Journal of Biomedical and Health Informatics.

[23]  Chris Donahue,et al.  Adversarial Audio Synthesis , 2018, ICLR.

[24]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[26]  Victor C. M. Leung,et al.  Design and evaluation of a novel wireless three-pad ECG system for generating conventional 12-lead signals , 2010, BODYNETS.

[27]  Patrick E. McSharry,et al.  A dynamical model for generating synthetic electrocardiogram signals , 2003, IEEE Transactions on Biomedical Engineering.

[28]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[29]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[30]  Tonio Ball,et al.  EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals , 2018, ArXiv.

[31]  Bin Zhou,et al.  BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series , 2019, IJCAI.

[32]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  G. Clifford,et al.  Generating 24-hour ECG, BP and respiratory signals with realistic linear and nonlinear clinical characteristics using a nonlinear model , 2004, Computers in Cardiology, 2004.

[34]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[35]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[36]  Shamim Nemati,et al.  An artificial vector model for generating abnormal electrocardiographic rhythms. , 2010, Physiological measurement.