Research on electrocardiogram classification using deep residual network with pyramid convolution structure_Journal of Biomedical Engineering

Authors：

 JIANG Mingfeng ¹ , LU Yi ¹ , LI Yang ¹ , XIANG Yikun ¹ , ZHANG Jucheng ² , WANG Zhikang ²

1. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, P.R.China;
2. Department of Clinical Engineering, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou 310019, P.R.China;

Corresponding author：

JIANG Mingfeng, Email: m.jiang@zstu.edu.cn

Keywords：

deep neural network; electrocardiogram classification; pyramid convolution; residual network

DOI：

10.7507/1001-5515.201912048

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Recently, deep neural networks (DNNs) have been widely used in the field of electrocardiogram (ECG) signal classification, but the previous models have limited ability to extract features from raw ECG data. In this paper, a deep residual network model based on pyramidal convolutional layers (PC-DRN) was proposed to implement ECG signal classification. The pyramidal convolutional (PC) layer could simultaneously extract multi-scale features from the original ECG data. And then, a deep residual network was designed to train the classification model for arrhythmia detection. The public dataset provided by the physionet computing in cardiology challenge 2017(CinC2017) was used to validate the classification experiment of 4 types of ECG data. In this paper, the harmonic mean F₁ of classification accuracy and recall was selected as the evaluation indexes. The experimental results showed that the average sequence level F₁ (SeqF₁) of PC-DRN was improved from 0.857 to 0.920, and the average set level F₁ (SetF₁) was improved from 0.876 to 0.925. Therefore, the PC-DRN model proposed in this paper provided a promising way for the feature extraction and classification of ECG signals, and provided an effective tool for arrhythmia classification.

Citation： JIANG Mingfeng, LU Yi, LI Yang, XIANG Yikun, ZHANG Jucheng, WANG Zhikang. Research on electrocardiogram classification using deep residual network with pyramid convolution structure. Journal of Biomedical Engineering, 2020, 37(4): 692-698. doi: 10.7507/1001-5515.201912048 Copy

1.	Alfaras M, Soriano M C, Ortín S. A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection. Frontiers in Physics, 2019, 7: 103.
2.	Zihlmann M, Perekrestenko D, Tschannen M. Convolutional recurrent neural networks for electrocardiogram classification//2017 Computing in Cardiology Conference (CinC), Rennes: IEEE, 2017: 1-4.
3.	马金伟, 刘盛平. 心电信号识别分类算法综述. 重庆理工大学学报: 自然科学版, 2018, 32(12): 122-128.
4.	赖杰伟, 陈韵岱, 韩宝石, 等. 基于 DenseNet 的心电数据自动诊断算法. 南方医科大学学报, 2019, 39(1): 69-75.
5.	Kumar M, Pachori R B, Acharya U R. Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform. Biocybern Biomed Eng, 2018, 38(3): 564-573.
6.	Piccini J P, Fauchier L. Rhythm control in atrial fibrillation. Lancet, 2016, 388(146): 829-840.
7.	Bonomi A G, Schipper F, Eerikäinen L M, <italic>et al</italic>. Atrial fibrillation detection using a novel cardiac ambulatory monitor based on photo-plethysmography at the wrist. J Am Heart Assoc, 2018, 7(15): e009351.
8.	Bizopoulos P, Koutsouris D. Deep learning in cardiology. IEEE Rev Biomed Eng, 2019, 12: 168-193.
9.	de Fauwj, Ledsam J R, Romera-Paredes B, <italic>et al</italic>. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med, 2018, 24(9): 1342-1350.
10.	Krittanawong C. The rise of artificial intelligence and the uncertain future for physicians. Eur J Intern Med, 2018, 48: e13-e14.
11.	Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng, 2016, 63(3): 664-675.
12.	Hannun A Y, Rajpurkar P, Haghpanahi M, <italic>et al</italic>. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 2019, 25(1): 65-69.
13.	Zhang Qingxue, Zhou Dian, Zeng Xuan. PulsePrint: single-arm-ECG biometric human identification using deep learning//2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York: IEEE, 2017: 452-456.
14.	Liu Wenhan, Zhang Mengxin, Zhang Yidan, <italic>et al</italic>. Real-time multilead convolutional neural network for myocardial infarction detection. IEEE J Biomed Health Inform, 2018, 22(5): 1434-1444.
15.	Wu M H, Chang E J, Chu T H. Personalizing a generic ECG heartbeat classification for arrhythmia detection: a deep learning approach//2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Miami: IEEE, 2018: 92-99.
16.	Wu M H, Chang E Y. Deepq arrhythmia database: a large-scale dataset for arrhythmia detector evaluation// Proceedings of the 2nd International Workshop on Multimedia for Personal Health and Health Care, California: ACM, 2017: 77-80.
17.	Al Rahhal M M, Bazi Y, AlHichri H, <italic>et al</italic>. Deep learning approach for active classification of electrocardiogram signals. Information sciences, 2016, 345: 340-354.
18.	Acharya U R, Fujita H, Lih O S, <italic>et al</italic>. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Information sciences, 2017, 405: 81-90.
19.	Luo Kan, Li Jianqing, Wang Zhigang, <italic>et al</italic>. Patient-specific deep architectural model for ECG classification. J Healthc Eng, 2017, 2017: 4108720.
20.	Xia Y, Wulan N, Wang Kuanquan, <italic>et al</italic>. Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med, 2018, 93: 84-92.
21.	Isin A, Ozdalili S. Cardiac arrhythmia detection using deep learning. Procedia Comput Sci, 2017, 120: 268-275.
22.	Xiao R, Xu Yuan, Pelter M M, <italic>et al</italic>. Monitoring significant ST changes through deep learning. J Electrocardiol, 2018, 51(6S): S78-S82.
23.	Liu Yixiu, Huang Yujuan, Wang Jianyi, <italic>et al</italic>. Detecting premature ventricular contraction in children with deep learning. J Shanghai Jiaotong Univ: Science, 2018, 23(1): 66-73.
24.	王媛媛, 周涛, 陆惠玲, 等. 基于集成卷积神经网络的肺部肿瘤计算机辅助诊断模型. 生物医学工程学杂志, 2017, 34(4): 543-551.
25.	李端, 张洪欣, 刘知青, 等. 基于深度残差卷积神经网络的心电信号心律不齐识别. 生物医学工程学杂志, 2019, 36(2): 189-198.
26.	Clifford G, Liu Chengyu, Moody B, et al. AF classification from a short single lead ECG recording: the PhysioNet / Computing in cardiology challenge 2017//2017 Computing in Cardiology Conference (CinC), Rennes: IEEE, 2017: 1-4.
27.	Berkaya S K, Uysal A K, Gunal E S, <italic>et al</italic>. A survey on ECG analysis. Biomedical Signal Processing and Control, 2018, 43: 216-235.

1. Alfaras M, Soriano M C, Ortín S. A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection. Frontiers in Physics, 2019, 7: 103.
2. Zihlmann M, Perekrestenko D, Tschannen M. Convolutional recurrent neural networks for electrocardiogram classification//2017 Computing in Cardiology Conference (CinC), Rennes: IEEE, 2017: 1-4.
3. 马金伟, 刘盛平. 心电信号识别分类算法综述. 重庆理工大学学报: 自然科学版, 2018, 32(12): 122-128.
4. 赖杰伟, 陈韵岱, 韩宝石, 等. 基于 DenseNet 的心电数据自动诊断算法. 南方医科大学学报, 2019, 39(1): 69-75.
5. Kumar M, Pachori R B, Acharya U R. Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform. Biocybern Biomed Eng, 2018, 38(3): 564-573.
6. Piccini J P, Fauchier L. Rhythm control in atrial fibrillation. Lancet, 2016, 388(146): 829-840.
7. Bonomi A G, Schipper F, Eerikäinen L M, <italic>et al</italic>. Atrial fibrillation detection using a novel cardiac ambulatory monitor based on photo-plethysmography at the wrist. J Am Heart Assoc, 2018, 7(15): e009351.
8. Bizopoulos P, Koutsouris D. Deep learning in cardiology. IEEE Rev Biomed Eng, 2019, 12: 168-193.
9. de Fauwj, Ledsam J R, Romera-Paredes B, <italic>et al</italic>. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med, 2018, 24(9): 1342-1350.
10. Krittanawong C. The rise of artificial intelligence and the uncertain future for physicians. Eur J Intern Med, 2018, 48: e13-e14.
11. Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng, 2016, 63(3): 664-675.
12. Hannun A Y, Rajpurkar P, Haghpanahi M, <italic>et al</italic>. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 2019, 25(1): 65-69.
13. Zhang Qingxue, Zhou Dian, Zeng Xuan. PulsePrint: single-arm-ECG biometric human identification using deep learning//2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York: IEEE, 2017: 452-456.
14. Liu Wenhan, Zhang Mengxin, Zhang Yidan, <italic>et al</italic>. Real-time multilead convolutional neural network for myocardial infarction detection. IEEE J Biomed Health Inform, 2018, 22(5): 1434-1444.
15. Wu M H, Chang E J, Chu T H. Personalizing a generic ECG heartbeat classification for arrhythmia detection: a deep learning approach//2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Miami: IEEE, 2018: 92-99.
16. Wu M H, Chang E Y. Deepq arrhythmia database: a large-scale dataset for arrhythmia detector evaluation// Proceedings of the 2nd International Workshop on Multimedia for Personal Health and Health Care, California: ACM, 2017: 77-80.
17. Al Rahhal M M, Bazi Y, AlHichri H, <italic>et al</italic>. Deep learning approach for active classification of electrocardiogram signals. Information sciences, 2016, 345: 340-354.
18. Acharya U R, Fujita H, Lih O S, <italic>et al</italic>. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Information sciences, 2017, 405: 81-90.
19. Luo Kan, Li Jianqing, Wang Zhigang, <italic>et al</italic>. Patient-specific deep architectural model for ECG classification. J Healthc Eng, 2017, 2017: 4108720.
20. Xia Y, Wulan N, Wang Kuanquan, <italic>et al</italic>. Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med, 2018, 93: 84-92.
21. Isin A, Ozdalili S. Cardiac arrhythmia detection using deep learning. Procedia Comput Sci, 2017, 120: 268-275.
22. Xiao R, Xu Yuan, Pelter M M, <italic>et al</italic>. Monitoring significant ST changes through deep learning. J Electrocardiol, 2018, 51(6S): S78-S82.
23. Liu Yixiu, Huang Yujuan, Wang Jianyi, <italic>et al</italic>. Detecting premature ventricular contraction in children with deep learning. J Shanghai Jiaotong Univ: Science, 2018, 23(1): 66-73.
24. 王媛媛, 周涛, 陆惠玲, 等. 基于集成卷积神经网络的肺部肿瘤计算机辅助诊断模型. 生物医学工程学杂志, 2017, 34(4): 543-551.
25. 李端, 张洪欣, 刘知青, 等. 基于深度残差卷积神经网络的心电信号心律不齐识别. 生物医学工程学杂志, 2019, 36(2): 189-198.
26. Clifford G, Liu Chengyu, Moody B, et al. AF classification from a short single lead ECG recording: the PhysioNet / Computing in cardiology challenge 2017//2017 Computing in Cardiology Conference (CinC), Rennes: IEEE, 2017: 1-4.
27. Berkaya S K, Uysal A K, Gunal E S, <italic>et al</italic>. A survey on ECG analysis. Biomedical Signal Processing and Control, 2018, 43: 216-235.

Journal of Biomedical Engineering

Research on electrocardiogram classification using deep residual network with pyramid convolution structure

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content