Browse > Article
http://dx.doi.org/10.3837/tiis.2022.05.002

A ResNet based multiscale feature extraction for classifying multi-variate medical time series  

Zhu, Junke (School of Computer Science, and Department of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology)
Sun, Le (School of Computer Science, and Department of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology)
Wang, Yilin (School of Computer Science, and Department of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology)
Subramani, Sudha (Victoria University)
Peng, Dandan (School of Computer Science and Network Engineering, Guangzhou University)
Nicolas, Shangwe Charmant (School of Computer Science, and Department of Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.16, no.5, 2022 , pp. 1431-1445 More about this Journal
Abstract
We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.
Keywords
Multi-scale convolutional feature extraction methods; ResNet50 structure; Squeeze-and-Excitation Modules;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Cao X C, Yao B, Chen B Q., "Atrial fibrillation detection using an improved multi-scale decomposition enhanced residual convolutional neural network," IEEE Access, 7, 89152-89161, 2019.   DOI
2 L. Sun, Y.L. Wang, Z.G. Qu, N.N. Xiong, "BeatClass: A Sustainable ECG Classification System in IoT-based eHealth," IEEE Internet of Things Journal, Aug. 2021.
3 Z. G. Qu, Y. M. Huang and M. Zheng, "A novel coherence-based quantum steganalysis protocol," Quantum Information Processing, vol.19, no. 362, pp. 1-19, 2020.   DOI
4 P. Lu, "A Position Self-Adaptive Method to Detect Fake Access Points," Journal of Quantum Computing, vol. 2, no. 2, pp. 119-127, 2020.   DOI
5 Yusuf, S., et al., "Global Burden of Cardiovascular Diseases," Circulation, 104(22), 2746-2753, 2001.   DOI
6 Okada, M., "A digital filter for the QRS complex detection," IEEE transactions on bio-medical engineering, BME-26(12), 700-703, 1979.   DOI
7 Rajpurkar P, Hannun A Y, Haghpanahi M, et al., "Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks," 2017.
8 Andersen RS, Peimankar A, Puthusserypady S., "A deep learning approach for real-time detection of atrial fibrillation," Expert Systems with Applications, 115, 465-473, 2019.   DOI
9 Clifford, Gari D., et al., "AF classification from a short single lead ECG recording: The PhysioNet/Computing in cardiology challenge 2017," in Proc. of 2017 Computing in Cardiology (CinC), IEEE, 2017.
10 Vaswani, Ashish, et al., "Attention is all you need," Advances in neural information processing systems, 2017.
11 He, Kaiming, et al., "Deep residual learning for image recognition," in Proc. of the IEEE conference on computer vision and pattern recognition, 2016.
12 Lin TY, Dollar P, Girshick R, et al., "Feature Pyramid Networks for Object Detection," in Proc. of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, 2017.
13 Xiong, Zhaohan, et al., "ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network," Physiological measurement, 39(9), 094006, 2018.   DOI
14 Darmawahyuni A, Nurmaini S, Sukemi, et al., "Deep learning with a recurrent network structure in the sequence modeling of imbalanced data for ECG-rhythm classifier," Algorithms, 12(6),1-12, 2019.
15 Wenjun Tan, Luyu Zhou, Xiaoshuo Li, Xiaoyu Yang, Yufei Chen, Jinzhu Yang, "Automated vessel segmentation in lung CT and CTA images via deep neural networks," Journal of X-Ray Science and Technology, 29(6), 1123-1137, 2021.
16 L. Sun, Q. Yu, D. Peng, S. Subramani and X. Wang, "Fogmed: a fog-based framework for disease prognosis based medical sensor data streams," Computers, Materials & Continua, vol. 66, no.1, pp. 603-619, 2021.
17 World Health Organization. Cardiovascular diseases (CVDs)[EB/OL] (2017-05-17)[2019-10-13]. [Online]. Available: https://www.who.int/en/news-room/fact-sheets/detail/cardiovasculardiseases-(cvds)
18 Ahlstrom, M. L., and W. J. Tompkins, "Digital filters for real-time ECG signal processing using microprocessors," IEEE transactions on bio-medical engineering, BME-32(9), 708-713, 1985.   DOI
19 Li Z, Zhou DS, Wan L, et al., "Heartbeat classification using deep residual convolutional neural network from 2-lead electrocardiogram," Journal of Electrocardiology, 58, 105-112, 2020.   DOI
20 Mathews S M, Kambhamettu C, Barner K E., "A novel application of deep learning for single-lead ECG classification," Computers in Biology and Medicine, 99, 53-62, 2018.   DOI
21 Rajpurkar, Pranav, et al., "Cardiologist-level arrhythmia detection with convolutional neural networks," arXiv preprint arXiv:1707.01836, 2017.
22 Fujino, Akinori, Hideki Isozaki, and Jun Suzuki, "Multi-label text categorization with model combination based on f1-score maximization," in Proc. of the Third International Joint Conference on Natural Language Processing: Volume-II, 2008.
23 Z. G. Qu, Z. W. Cheng, W. J. Liu, X. J. Wang, "A novel quantum image steganography algorithm based on exploiting modification direction," Multimedia Tools and Applications, vol. 78, no. 1, pp. 7981-8001, 2019.   DOI
24 Jie H, Li S, Gang S, et al., "Squeeze-and-Excitation Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(8), 2011-2023, 2020.   DOI
25 P Plawiak, "Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals," Swarm and Evolutionary Computation, 39, 192-208, 2018.   DOI
26 Feng, Yingjing, and Edward Vigmond, "Deep Multi-Label Multi-Instance Classification on 12-Lead ECG," in Proc. of 2020 Computing in Cardiology, IEEE, 2020.
27 Xiong, Zhaohan, Martin K. Stiles, and Jichao Zhao, "Robust ECG signal classification for detection of atrial fibrillation using a novel neural network," in Proc. of 2017 Computing in Cardiology (CinC), IEEE, 2017.
28 Sun L., Zhong Z., Qu Z. and Xiong N., "PerAE: An Effective Personalized AutoEncoder for ECG-based Biometric in Augmented Reality System," IEEE Journal of Biomedical and Health Informatics, Jan. 2022.
29 Zhao, Zhibin, et al., "Adaptive lead weighted ResNet trained with different duration signals for classifying 12-lead ECGs," in Proc. of 2020 Computing in Cardiology, IEEE, 2020.
30 Ishida, Takashi, et al., "Do we need zero training loss after achieving zero training error?," arXiv preprint arXiv:2002.08709, 2020.
31 Acharya UR, Fujita H, Lih O S, et al., "Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network," INFORMATION SCIENCES, 405, 81-90, 2017.   DOI
32 Melgani F, Bazi Y, "Classification of electrocardiogram signals with support vector machines and particle swarm optimization," IEEE transactions on information technology in biomedicine, 12(5), 667-677, 2008.   DOI
33 Kumar RG, Kumaraswamy YS, "Investigating cardiac arrhythmia in ECG using random forest classification," International Journal of Computer Applications, 37(4), 31-34, 2012.   DOI
34 Singstad, Bjorn-Jostein, and Christian Tronstad, "Convolutional Neural Network and Rule-Based Algorithms for Classifying 12-lead ECGs," in Proc. of 2020 Computing in Cardiology, IEEE, 2020.
35 Wenjun Tan, Peifang Huang, Xiaoshuo Li, Genqiang Ren, Yufei Chen, Jinzhu Yang, "Analysis of Segmentation of Lung Parenchyma Based on Deep Learning Methods," Journal of X-Ray Science and Technology, 2021(1), 945-959, 2021.