Parallel classification model of arrhythmia based on DenseNet-BiLSTM

• Autorzy: Gan Yi , Shi Jun-Cheng , He Wei-Ming , Sun Fu-Jia

Identyfikatory

DOI

10.1016/j.bbe.2021.09.001

• Języki publikacji: EN

Abstrakty

EN

In order to improve the classification performance of the model for different kinds of arrhythmias, a parallel classification model of arrhythmia based on DenseNet-BiLSTM is researched and proposed. Firstly, the model adopts a parallel structure. After wavelet denoising and heartbeat segmentation of ECG signals, this model can simultaneously capture the waveform features of small-scale heartbeat and large-scale heartbeat containing RR interval; Then, based on deep learning, Densely connected convolutional network (DenseNet) is applied to improve the model’s ability to extract local features of ECG signals, and bidirectional long short-term memory network (BiLSTM) is introduced to improve the performance of the model in extracting time series features of ECG signals; Finally, weighted cross entropy loss function is used to alleviate the class imbalance of arrhythmia, and Softmax function is applied to achieve 4 classifications of arrhythmia. Experiments based on MIT-BIH arrhythmia database show that under the intra-patient paradigm, training time for each epoch, overall accuracy, F₁ and specificity are 42 s, 99.44%, 95.89% and 99.32%, respectively; Under the inter-patient paradigm, training time for each epoch, overall accuracy, F₁ and specificity are 23 s, 92.37%, 63.49% and 94.51%, respectively. Compared with other classification models, the model proposed in this paper has a good classification effect and is expected to be used in clinical auxiliary diagnosis.

Słowa kluczowe

EN

cardiac arrhythmia; parallel classification; DenseNet; BiLSTM; weighted cross entropy loss function

PL

arytmia serca; klasyfikacja równoległa; DenseNet; BiLSTM

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 4
• Strony: 1548--1560
• Opis fizyczny: Bibliogr. 47 poz., rys., tab., wykr.

Twórcy

autor

Gan Yi

• School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China; Faculty of Science and Engineering, Chuo University, Tokyo, Japan

autor

Shi Jun-Cheng

• School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China

autor

He Wei-Ming

• School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China; Faculty of Science and Engineering, Chuo University, Tokyo, Japan

autor

Sun Fu-Jia

• School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China

Bibliografia

• [1] Ribeiro AH, Ribeiro MH, Paixão GMM, Oliveira DM, Gomes PR, Canazart JA, et al. Author Correction: Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun 2020;11. https://doi.org/10.1038/s41467-020-16172-1.
• [2] Allam JP, Samantray S, Ari S. SpEC: A system for patient specific ECG beat classification using deep residual network. Biocybern Biomed Eng 2020;40:1446–57. https://doi.org/10.1016/j.bbe.2020.08.001.
• [3] Panda R, Jain S, Tripathy RK, Acharya UR. Detection of shockable ventricular cardiac arrhythmias from ECG signals using FFREWT filter-bank and deep convolutional neural network. Comput Biol Med 2020;124:103939. https://doi.org/10.1016/j.compbiomed.2020.103939.
• [4] Marinho LB, Nascimento NdeMM, Souza JWM, Gurgel MV, Rebouças Filho PP, de Albuquerque VHC. A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification. Future Gener Comput Syst 2019;97:564–77. https://doi.org/10.1016/j.future.2019.03.025.
• [5] Huang J, Chen B, Yao B, He W. ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network. IEEE Access 2019;7:92871–80. https://doi.org/10.1109/ACCESS.2019.2928017.
• [6] Guo M-F, Yang N-C, You L-X. Wavelet-transform based early detection method for short-circuit faults in power distribution networks. Int J Electr Power Energy Syst 2018;99:706–21. https://doi.org/10.1016/j.ijepes.2018.01.013.
• [7] Rahul J, Sora M, Sharma LD, Bohat VK. An improved cardiac arrhythmia classification using an RR interval-based approach. Biocybern Biomed Eng 2021;41(2):656–66. https://doi.org/10.1016/j.bbe.2021.04.004.
• [8] Xiong P, Xue Y, Zhang J, Liu M, Du H, Zhang H, et al. Localization of myocardial infarction with multi-lead ECG based on DenseNet. Comput Methods Programs Biomed 2021;203:106024. https://doi.org/10.1016/j.cmpb.2021.106024.
• [9] Guo L, Lei B, Chen W, Du J, Frangi AF, Qin J, et al. Dual attention enhancement feature fusion network for segmentation and quantitative analysis of paediatric echocardiography. Med Image Anal 2021;71:102042. https://doi.org/10.1016/j.media.2021.102042.
• [10] Rahim T, Hassan SA, Shin SY. A deep convolutional neural network for the detection of polyps in colonoscopy images. Biomed Signal Process Control 2021;68:102654. https://doi.org/10.1016/j.bspc.2021.102654.
• [11] Hernandez-Matamoros A, Fujita H, Escamilla-Hernandez E, Perez-Meana H, Nakano-Miyatake M. Recognition of ECG signals using wavelet based on atomic functions. Biocybern Biomed Eng 2020;40:803–14. https://doi.org/10.1016/j.bbe.2020.02.007.
• [12] Guo L, Sim G, Matuszewski B. Inter-patient ECG classification with convolutional and recurrent neural networks. Biocybern Biomed Eng 2019;39:868–79. https://doi.org/10.1016/j.bbe.2019.06.001.
• [13] Asgharzadeh-Bonab A, Amirani MC, Mehri A. Spectral entropy and deep convolutional neural network for ECG beat classification. Biocybern Biomed Eng 2020;40:691–700. https://doi.org/10.1016/j.bbe.2020.02.004.
• [14] Liu H, Zhao Z, Chen X, Yu R, She Q. Using the VQ-VAE to improve the recognition of abnormalities in short-duration 12-lead electrocardiogram records. Comput Methods Programs Biomed 2020;196:105639. https://doi.org/10.1016/j.cmpb.2020.105639.
• [15] Luz EJdS, Schwartz WR, Cámara-Chávez G, Menotti D. ECG-based heartbeat classification for arrhythmia detection: A survey. Comput Methods Programs Biomed 2016;127:144–64. https://doi.org/10.1016/j.cmpb.2015.12.008.
• [16] Hao H, Liu M, Xiong P, Du H, Zhang H, Lin F, et al. Multi-lead model-based ECG signal denoising by guided filter. Eng Appl Artif Intell 2019;79:34–44. https://doi.org/10.1016/j.engappai.2018.12.004.
• [17] de Chazal P, O’Dwyer M, Reilly RB. Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features. IEEE Trans Biomed Eng 2004;51:1196–206. https://doi.org/10.1109/TBME.2004.827359.
• [18] Sharma RR, Kumar A, Pachori RB, Acharya UR. Accurate automated detection of congestive heart failure using eigenvalue decomposition based features extracted from HRV signals. Biocybern Biomed Eng 2019;39:312–27. https://doi.org/10.1016/j.bbe.2018.10.001.
• [19] Kumar M, Pachori RB, Rajendra Acharya U. Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform. Biocybern Biomed Eng 2018;38:564–73. https://doi.org/10.1016/j.bbe.2018.04.004.
• [20] Xu L, Bai L, Jiang X, Tan M, Zhang D, Luo B. Deep Rényi entropy graph kernel. Pattern Recogn 2021;111:107668. https://doi.org/10.1016/j.patcog.2020.107668.
• [21] Tripathy RK. Application of intrinsic band function technique for automated detection of sleep apnea using HRV and EDR signals. Biocybern Biomed Eng 2018;38:136–44. https://doi.org/10.1016/j.bbe.2017.11.003.
• [22] Sharma M, Tan R-S, Acharya UR. Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters. Inf Med Unlocked 2019;16:100221. https://doi.org/10.1016/j.imu.2019.100221.
• [23] Jha CK, Kolekar MH. Cardiac arrhythmia classification using tunable Q-wavelet transform based features and support vector machine classifier. Biomed Signal Process Control 2020;59:101875. https://doi.org/10.1016/j.bspc.2020.101875.
• [24] Yang W, Si Y, Wang D, Guo B. Automatic recognition of arrhythmia based on principal component analysis network and linear support vector machine. Comput Biol Med 2018;101:22–32. https://doi.org/10.1016/j.compbiomed.2018.08.003.
• [25] Yang W, Si Y, Wang D, Zhang G. A novel method for identifying electrocardiograms using an independent component analysis and principal component analysis network. Measurement 2020;152:107363. https://doi.org/10.1016/j.measurement.2019.107363.
• [26] Czabanski R, Horoba K, Wrobel J, Matonia A, Martinek R, Kupka T, et al. Detection of atrial fibrillation episodes in long-term heart rhythm signals using a support vector machine. Sensors 2020;20:765. https://doi.org/10.3390/s20030765.
• [27] Shi J, Chen C, Liu H, Wang Y, Shu M, Zhu Q, et al. Automated atrial fibrillation detection based on feature fusion using discriminant canonical correlation analysis. Comput Math Methods Med 2021;2021:1–10. https://doi.org/10.1155/2021/6691177.
• [28] Dias FM, Monteiro HLM, Cabral TW, Naji R, Kuehni M, Luz EJ da S. Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm. Comput Methods Programs Biomed 2021;202:105948. https://doi.org/10.1016/j.cmpb.2021.105948.
• [29] Raj S, Ray KC. Sparse representation of ECG signals for automated recognition of cardiac arrhythmias. Expert Syst Appl 2018;105:49–64. https://doi.org/10.1016/j.eswa.2018.03.038.
• [30] Shi H, Wang H, Huang Y, Zhao L, Qin C, Liu C. A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification. Comput Methods Programs Biomed 2019;171:1–10. https://doi.org/10.1016/j.cmpb.2019.02.005.
• [31] Chen S, Hua W, Li Z, Li J, Gao X. Heartbeat classification using projected and dynamic features of ECG signal. Biomed Signal Process Control 2017;31:165–73. https://doi.org/10.1016/j.bspc.2016.07.010.
• [32] Ma H, Chen C, Zhu Q, Yuan H, Chen L, Shu M, et al. An ECG signal classification method based on dilated causal convolution. Comput Math Methods Med 2021;2021:1–10. https://doi.org/10.1155/2021/6627939.
• [33] Zhang J, Liu A, Gao M, Chen X, Zhang X, Chen X. ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network. Artif Intell Med 2020;106:101856. https://doi.org/10.1016/j.artmed.2020.101856.
• [34] Zhou S, Tan B. Electrocardiogram soft computing using hybrid deep learning CNN-ELM. Appl Soft Comput 2020;86:105778. https://doi.org/10.1016/j.asoc.2019.105778.
• [35] Wang H, Shi H, Chen X, Zhao L, Huang Y, Liu C. An improved convolutional neural network based approach for automated heartbeat classification. J Med Syst 2019:35–44. https://doi.org/10.1007/s10916-019-1511-2.
• [36] Jing E, Zhang H, Li Z, Liu Y, Ji Z, Ganchev I, et al. ECG heartbeat classification based on an improved ResNet-18 model. Comput Math Methods Med 2021;2021:1–13. https://doi.org/10.1155/2021/6649970.
• [37] Sellami A, Hwang H. A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Expert Syst Appl 2019;122:75–84. https://doi.org/10.1016/j.eswa.2018.12.037.
• [38] Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 2019;25:65–9. https://doi.org/10.1038/s41591-018-0268-3.
• [39] Atal DK, Singh M. Arrhythmia classification with ECG signals based on the optimization-enabled deep convolutional neural network. Comput Methods Programs Biomed 2020;196:105607. https://doi.org/10.1016/j.cmpb.2020.105607.
• [40] Goodfellow S, Goodwin A, Greer R, Laussen P, Mazwi M, Eytan D. Towards understanding ECG rhythm classification using convolutional neural networks and attention mappings. Proc Mach Learn Res 2018;85:1–18.
• [41] Yan Z, Zhou J, Wong W-F. Energy efficient ECG classification with spiking neural network. Biomed Signal Process Control 2021;63:102170. https://doi.org/10.1016/j.bspc.2020.102170.
• [42] Chen A, Wang F, Liu W, Chang S, Wang H, He J, et al. Multi-information fusion neural networks for arrhythmia automatic detection. Comput Methods Programs Biomed 2020;193:105479. https://doi.org/10.1016/j.cmpb.2020.105479.
• [43] Boda S, Mahadevappa M, Dutta PK. A hybrid method for removal of power line interference and baseline wander in ECG signals using EMD and EWT. Biomed Signal Process Control 2021;67:102466. https://doi.org/10.1016/j.bspc.2021.102466.
• [44] Singhal A, Singh P, Fatimah B, Pachori RB. An efficient removal of power-line interference and baseline wander from ECG signals by employing Fourier decomposition technique. Biomed Signal Process Control 2020;57:101741. https://doi.org/10.1016/j.bspc.2019.101741.
• [45] Chen X, Lin J, Huang C, He L. A novel method based on adaptive periodic segment matrix and singular value decomposition for removing EMG artifact in ECG signal. Biomed Signal Process Control 2020;62:102060. https://doi.org/10.1016/j.bspc.2020.102060.
• [46] Wang H, Shi H, Lin Ke, Qin C, Zhao L, Huang Y, et al. A high-precision arrhythmia classification method based on dual fully connected neural network. Biomed Signal Process Control 2020;58:101874. https://doi.org/10.1016/j.bspc.2020.101874.
• [47] Thurner T, Hintermueller C, Blessberger H, Steinwender C. Complex-Pan-Tompkins-Wavelets: Cross-channel ECG beat detection and delineation. Biomed Signal Process Control 2021;66:102450. https://doi.org/10.1016/j.bspc.2021.102450.