心电信号降噪算法研究综述

doi:10.11896/jsjkx.220300094

摘要/Abstract

摘要： 心电信号(Electrocardiogram,ECG)作为识别人体心脏异常的重要指标,其最常见的一个处理问题是消除不必要的噪声。这些噪声会使干净信号失真,从而影响对人体心脏的诊断与分析。综述了5种不同的心电信号降噪技术框架以及在该框架下的最新研究成果,最后汇总了近5年优秀降噪模型,并通过信噪比等性能评价标准进行比较。对比显示,不管基于单一噪声或是复合噪声,深度学习模型在降噪方面均显现出良好性能。最后,讨论了当前降噪模型存在的不足,并对下一步研究进行了展望。

关键词: 心电信号, 深度学习, 降噪, 信噪比

Abstract: One of the most common signal processing problems with the electrocardiogram(ECG),an important indicator for identifying cardiac abnormalities in humans,is the elimination of unwanted noise.These noises can distort the clean signal,which can affect the diagnosis and analysis of the human heart.This paper reviews five different frameworks of ECG signal denoising techniques and the latest research results within these frameworks,and finally summarizes the best noise reduction models in last five years and compares them by performance evaluation criteria such as signal-to-noise ratio.The comparison shows that the deep learning models show good performance in ECG denoising,whether based on single noise or composite noise.Finally,the problems with the current denoising model are discussed and an outlook on the next step of the research is given.

Key words: Electrocardiogram(ECG), Deep learning, Denoising, Signal-to-noise ratio

中图分类号:

TP301.6

侯彦荣, 刘瑞霞, 舒明雷, 陈长芳, 单珂. 心电信号降噪算法研究综述[J]. 计算机科学, 2023, 50(6A): 220300094-11. https://doi.org/10.11896/jsjkx.220300094

HOU Yanrong, LIU Ruixia, SHU Minglei, CHEN Changfang, SHAN Ke. Review of Research on Denoising Algorithms of ECG Signal[J]. Computer Science, 2023, 50(6A): 220300094-11. https://doi.org/10.11896/jsjkx.220300094

参考文献

[1]HOSNY K M,KHALID A M,MOHAMED E R.Efficient compression of bio-signals by using Tchebichef moments and Artificial Bee Colony[J].Biocybernetics and Biomedical Engineering,2018,38(2):385-398.
[2]SARITHA C,SUKANYA V,MURTHY Y N.ECG signal analy-sis using wavelet transforms[J].Bulg.J.Phys,2008,35(1):68-77.
[3]LIU J,YIN L,HE C,et al.A multiscale autoregressive model-based electrocardiogram identification method[J].IEEE Access,2018,6:18251-18263.
[4]CLIFFORD G D,AZUAJE F,MCSHARRY P.ECG statistics,noise,artifacts,and missing data[J].Advanced Methods and Tools for ECG Data Analysis,2006,6(1):18.
[5]SATIJA U,RAMKUMAR B,MANIKANDAN M S.A review of signal processing techniques for electrocardiogram signal quality assessment[J].IEEE Reviews in Biomedical Enginee-ring,2018,11:36-52.
[6]GACEK A,PEDRYCZ W.ECG signal processing,classification and interpretation:a comprehensive framework of computational intelligence[M].Springer Science & Business Media,2011.
[7]JOY J,MANIMEGALAI P.Wavelet based EMG artifact remo-val from ECG signal[J].J Eng Comp & Appl Sci,2013,2:55-58.
[8]MAKDESSY C,CAO H,PEYRODIE L,et al.A comparativeanalysis of ECG denoising methods[C]//2020 IEEE 20th International Conference on Bioinformatics and Bioengineering(BIBE).IEEE,2020:853-858.
[9]CHATTERJEE S,THAKUR R S,YADAV R N,et al.Review of noise removal techniques in ECG signals[J].IET Signal Processing,2020,14(9):569-590.
[10]HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings of the Royal Society of London.Series A:Mathematical Physical and Enginee-ring Sciences,1998,454(1971):903-995.
[11]HUANG N E,NII O.Attoh-Okine,eds.The Hilbert-Huangtransform in engineering[M].Taylor & Francis,2005.
[12]DAVID L,DONOHO J.Denoising by soft-thresholding[J].IEEE Transactions on Information Theory,1995,41(3):613-627.
[13]LI G,ULLAH S M W,LI B,et al.Baseline Wander Removal for ECG Signals Based on Improved EMD[C]//2020 15th IEEE International Conference on Signal Processing(ICSP).IEEE,2020:484-487.
[14]ZHANG D,WANG S,LI F,et al.An Efficient ECG Denoising Method Based on Empirical Mode Decomposition,Sample Entropy,and Improved Threshold Function[J].Wireless Communications and Mobile Computing,2020,2020(2):1-11.
[15]YAO L,PAN Z.A new method based CEEMDAN for removal of baseline wander and powerline interference in ECG signals[J].Optik,2020,223:165566.
[16]TEJA K,TIWARI R,MOHANTY S.Adaptive denoising ofECG using EMD,EEMD and CEEMDAN signal processing techniques[J].Journal of Physics:Conference Series,2020,1706(1):012077.
[17]MOHGUEN W,BEKKA R E.Comparative Study of ECG Signal Denoising by Empirical Mode Decomposition and Thresholding Functions[C]//2019 6th International Conference on Electrical and Electronics Engineering(ICEEE).IEEE,2019:126-130.
[18]ZEBIN L,WEI L,LIFU G,et al.Research on ECG Denoisingmethod Based on Empirical Mode Decomposition and Wavelet Transform[C]//2020 IEEE 5th International Conference on Signal and Image Processing(ICSIP).IEEE,2020:675-679.
[19]VARGAS R N,VEIGA A C P.Electrocardiogram signal denoi-sing by clustering and soft thresholding[J].IET Signal Proces-sing,2018,12(9):1165-1171.
[20]THAKRAN S.A hybrid GPFA-EEMD_Fuzzy threshold method for ECG signal de-noising[J].Journal of Intelligent & Fuzzy Systems,2020,39(5):6773-6782.
[21]YIN J,CHEN X,ZHANG P,et al.Research on ECG Signal Denoising by Combination of EEMD and NLM[C]//2020 Chinese Control And Decision Conference(CCDC).IEEE,2020:5033-5038.
[22]RAKSHIT M,DAS S.An efficient ECG denoising methodology using empirical mode decomposition and adaptive switching mean filter[J].Biomedical Signal Processing and Control,2018,40:140-148.
[23]TAN Y,DU L.Study on wavelet transform in the processing for ECG signals[C]//2009 WRI World Congress on Software Engineering.IEEE,2009:515-518.
[24]DONOHO D L,JOHNSTONE J M.Ideal spatial adaptation by wavelet shrinkage[J].Biometrika,1994,81(3):425-455.
[25]NASON G P.Wavelet function estimation using cross-validation[M]//Wavelets andStatistics.Springer Verlag,1995:281-299.
[26]NASON G P.The wavethresh package;wavelet transform and thresholding software for S[J].Journal of Comkputational and Graphical Statistics,1994,3(2):163-191.
[27]VIDAKOVIC B.Nonlinear wavelet shrinkage with Bayes rules and Bayes factors[J].Journal of the American Statistical Association,1998,93(441):173-179.
[28]ABRAMOVICH F,BENJAMINI Y.Adaptive thresholding ofwavelet coefficients[J].Computational Statistics & Data Analysis,1996,22(4):351-361.
[29]DONOHO D L,JOHNSTONE I M.Adapting to unknownsmoothness via wavelet shrinkage[J].Journal of the American Statistical Association,1995,90(432):1200-1224.
[30]GON A,MUKHERJEE A.Removal of Noises from an ECG Signal Using an Adaptive S-Median Thresholding Technique[C]//2020 IEEE Applied Signal Processing Conference(ASPCON).IEEE,2020:89-93.
[31]LATIF R,JENKAL W,TOUMANARI A,et al.Electrocardiogram Signal Denoising Using a Hybrid Technique[J].International Journal of Bioengineering and Life Sciences,2017,11(3):256-259.
[32]KUMAR A,TOMAR H,MEHLA V K,et al.Stationary wavelet transform based ECG signal denoising method[J].ISA transactions,2021,114:251-262.
[33]PRASHAR N,SOOD M,JAIN S.Design and implementation of a robust noise removal system in ECG signals using dual-tree complex wavelet transform[J].Biomedical Signal Processing and Control,2021,63:102212.
[34]NAHAR A K.Adaptive symlet filter based on ECG baselinewander removal[J].Serbian Journal of Electrical Engineering,2020,17(2):187-197.
[35]CHEN C C,TSUI F R.Comparing different wavelet transforms on removing electrocardiogram baseline wanders and special trends[J].BMC Medical Informatics and Decision Making,2020,20(11):1-10.
[36]ZHUANG C,LIAO P.An improved empirical wavelet transform for noisy and non-stationary signal processing[J].IEEE Access,2020,8:24484-24494.
[37]VARGAS R N,VEIGA A C P.Electrocardiogram signal denoising by a new noise variation estimate[J].Research on BiomedicalEngineering,2020,36(1):13-20.
[38]TROPP J A,GILBERT A C,MARTIN J S,et al.Algorithms for simultaneous sparse approximation[C]//EURASIP J.App.Signal Processing.2006.
[39]SHI H.ECG Baseline Estimation and Denoising With Group Sparse Regularization[J].IEEE Access,2021(9):23595-23607.
[40]WANG X,ZHOU Y,SHU M,et al.ECG baseline wander correction and denoising based on sparsity[J].IEEE access,2019,7:31573-31585.
[41]SELESNICK I.Sparsity-assisted signal smoothing(revisited)[C]//2017 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2017:4546-4550.
[42]JIN Z Y.Sparse ECG denoising with generalized minimax concave penalty[J].Sensors,2019,19(7):1718.
[43]GUPTA R,NARAYANAN N,GUPTA P,et al.ModifiedAdaptive Dictionary Reconstruction Framework for Compressed Sensing of ECG Signals[C]//2020 International Conference on Communication and Signal Processing(ICCSP).Chennai,India,2020:0006-0011.
[44]SAMENI R,SHAMSOLLAHI M B,JUTTEN C,et al.A nonlinear Bayesian filtering framework for ECG denoising[J].IEEE Transactions on Biomedical Engineering,2007,54(12):2172-2185.
[45]OUALI M A,CHAFAA K,GHANAI M,et al.ECG denoising using extended Kalman filter[C]//2013 International Confe-rence on Computer Applications Technology(ICCAT).IEEE,2013:1-6.
[46]MANJU B R,SNEHA M R.ECG Denoising using Wiener filter and Kalman filter[J].Procedia Computer Science,2020,171:273-281.
[47]HESAR H D,MOHEBBI M.An adaptive Kalman filter bank for ECG denoising[J].IEEE Journal of Biomedical and Health Informatics,2020,25(1):13-21.
[48]BODILE R M,RAO T V K H.ECG Denoising Using Cubature Quadrature Kalman Filter Approach[C]//2020 IEEE India Council International Subsections Conference(INDISCON).IEEE,2020:216-220.
[49]LASTRE-DOMÍNGUEZ C,IBARRA-MANZANO O,AN-DRADE-LUCIO J A,et al.Denoising ECG Signals Using Unbiased FIR Smoother and Harmonic State-Space Model[C]//2020 28th European Signal Processing Conference(EUSIPCO).IEEE,2021:1279-1283.
[50]HESAR H D,MOHEBBI M.An adaptive particle weightingstrategy for ECG denoising using marginalized particle extended Kalman filter:An evaluation in arrhythmia contexts[J].IEEE Journal of Biomedical and Health Informatics,2017,21(6):1581-1592.
[51]VINCENT P,LAROCHELLE H,BENGIO Y,et al.Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning.2008:1096-1103.
[52]CASAS L.Adversarial signal denoising with encoder-decodernetworks[C]//2020 28th European Signal Processing Confe-rence(EUSIPCO).IEEE,2021.
[53]SINGH P,PRADHAN G.A new ECG denoising frameworkusing generative adversarial network[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2020,18(2):759-764.
[54]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial networks[J].arXiv:1406.2661,2014.
[55]WANG J,LI R,LI R,et al.Adversarial de-noising of electrocardiogram[J].Neurocomputing,2019,349:212-224.
[56]MAO X,LI Q,XIE H,et al.Least squares generative adversarial networks[C]//Proceedings of the IEEE International Confe-rence on Computer Vision.2017:2794-2802.
[57]PASCUAL S,BONAFONTE A,SERRA J.SEGAN:Speech enhancement generative adversarial network[J].arXiv:1703.09452,2017.
[58]ARSENE C.Design of Deep Convolutional Neural Network Architectures for Denoising Electrocardiographic Signals[C]//2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology(CIBCB).Via del Mar,Chile,2020:1-8.
[59]CHIANG H T.Noise reduction in ECG signals using fully convolutional denoising autoencoders[J].IEEE Access,2019(7):60806-60813.
[60]QIU L S.A two-stage ECG signal denoising method based on deep convolutional network[J].Physiological Measurement,2021,42(11):115002.
[61]KAROL A.Deep recurrent neural networks for ECG signal denoising[J].arXiv:1807.11551,2018.
[62]WANG G.ECG signal denoising based on deep factor analysis[J].Biomedical Signal Processing and Control,2020(57):101824.
[63]DWIVEDI,KUMAR A.Noise Reduction in ECG Signal Using Combined Ensemble Empirical Mode Decomposition Method with Stationary Wavelet Transform[J].Circuits,Systems,and Signal Processing,2021,40(2):827-844.
[64]SOMARAJU B,MANJUNATHA M,PRANAB K D.A hybrid method for removal of power line interference and baseline wander in ECG signals using EMD and EWT[J].Biomedical Signal Processing and Control,2021(67):102466.
[65]YIN J F.Research on ECG Signal Denoising by Combination of EEMD and NLM[C]//2020 Chinese Control And Decision Conference(CCDC).IEEE,2020.
[66]TALBI M,RIADH B,MED S B.A New Technique of ECG Denoising based on LWT and Total Variation Minimization ECG Denoising[C]//2020 21st International Arab Conference on Information Technology(ACIT).IEEE,2020.
[67]TELLALA I,AMARDJIA N,KESMIA A.Α Modified EMD-ACWA Denoising Scheme using a Noise-only Model[J].Engineering,Technology & Applied Science Research,2020,10(2):5470-5476.
[68]SINGH P,PRADHAN G.Variational mode decompositionbased ECG denoising using non-local means and wavelet domain filtering[J].Australasian Physical & Engineering Sciences in Medicine,2018,41(4):891-904.
[69]ALHUSSAINY A,JASIM A D.ECG signal denoising based on deep learning auto encoder and discrete wavelet transform[J].International Journal of Engineering & Technology,2020,9(2):415.
[70]ZHANG M,WEI G.An integrated EMD adaptive threshold denoising method for reduction of noise in ECG[J].Plos one,2020,15(7):e0235330.
[71]CONDAT L.A direct algorithm for 1-D total variation denoising[J].IEEE Signal Processing Letters,2013,20(11):1054-1057.
[72]HAN G,XU Z.Electrocardiogram signal denoising based on anew improved wavelet thresholding[J].Review of Scientific Instruments,2016,87(8):084303.
[73]GARCÍA M,MARTÍNEZ-INIESTA M,RDENAS J,et al.A novel wavelet-based filtering strategy to remove powerline interference from electrocardiograms with atrial fibrillation[J].Phy-siological Measurement,2018,39(11):115006.
[74]BLANCO-VELASCO M,WENG B,BARNER K E.ECG signal denoising and baseline wander correction based on the empirical mode decomposition[J].Computers in Biology and Medicine,2008,38(1):1-13.
[75]WU Z,HUANG N E.Ensemble empirical mode decomposition:a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,1(1):1-41.
[76]SINGH O,SUNKARIA R K.ECG signal denoising based on empirical mode decomposition and moving average filter[C]//2013 IEEE International Conference on Signal Processing,Computing and Control(ISPCC).IEEE,2013:1-6.
[77]KAERGAARD K,JENSEN S H,PUTHUSSERYPADY S.A comprehensive performance analysis of EEMD-BLMS and DWT-NN hybrid algorithms for ECG denoising[J].Biomedical Signal Processing and Control,2016,25:178-187.
[78]AMINDAVAR H,NARAGHI F.Wavelet-based variationalBayesian ECG denoising[C]//2017 3rd International Confe-rence on Pattern Recognition and Image Analysis(IPRIA).IEEE,2017:7-12.
[79]KUMAR S,PANIGRAHY D,SAHU P K.Denoising of Electrocardiogram(ECG) signal by using empirical mode decomposition(EMD) with non-local mean(NLM) technique[J].Biocybernetics and Biomedical Engineering,2018,38(2):297-312.
[80]SINGH P,PRADHAN G,SHAHNAWAZUDDIN S.Denoising of ECG signal by non-local estimation of approximation coefficients in DWT[J].Biocybernetics and Biomedical Engineering,2017,37(3):599-610.
[81]SAXENA S,JAIS R,HOTA M K.Removal of powerline interference from ECG signal using FIR,IIR,DWT and NLMS adaptive filter[C]//2019 International Conference on Communication and Signal Processing(ICCSP).IEEE,2019:12-16.
[82]RAKSHIT M,DAS S.Hybrid approach for ECG signal en-hancement using dictionary learning-based sparse representation[J].IET Science,Measurement & Technology,2019,13(3):381-391.
[83]SINGH O,SUNKARIA R K.ECG signal denoising via empirical wavelet transform[J].Australasian Physical & Engineering Sciences in Medicine,2017,40(1):219-229.
[84]BIROK R.ECG Denoising Using Artificial Neural Networks and Complete Ensemble Empirical Mode Decomposition[J].Turkish Journal of Computer and Mathematics Education(TURCOMAT),2021,12(2):2382-2389.
[85]BIROK R.ECG Denoising Using Artificial Neural Networks and Complete Ensemble Empirical Mode Decomposition[J].Turkish Journal of Computer and Mathematics Education(TURCOMAT),2021,12(2):2382-2389.
[86]OUALI M A,TINOUNA A,GHANAI M,et al.Electrocardiogram Signal Denoising by Hilbert Transform and Synchronous Detection[J].International Journal Bioautomation,2020,24(4):323.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed