Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning_Journal of Biomedical Engineering

Authors：

YANG Yong ^1,2,3 ,  QIN Xiaolin ^1,2 , LIN Xiaoguang ³ , WEN Han ^1,2 , PENG Yuncong ^1,2

1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610041, P. R. China;
2. University of Chinese Academy of Sciences, Beijing 100049, P. R. China;
3. Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, P. R. China;

Corresponding author：

QIN Xiaolin, Email: qinxl2001@126.com

Keywords：

Epileptic seizure; Electroencephalogram signal; Ensemble approach; Deep learning; Transfer learning

DOI：

10.7507/1001-5515.202107060

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In recent years, epileptic seizure detection based on electroencephalogram (EEG) has attracted the widespread attention of the academic. However, it is difficult to collect data from epileptic seizure, and it is easy to cause over fitting phenomenon under the condition of few training data. In order to solve this problem, this paper took the CHB-MIT epilepsy EEG dataset from Boston Children's Hospital as the research object, and applied wavelet transform for data augmentation by setting different wavelet transform scale factors. In addition, by combining deep learning, ensemble learning, transfer learning and other methods, an epilepsy detection method with high accuracy for specific epilepsy patients was proposed under the condition of insufficient learning samples. In test, the wavelet transform scale factors 2, 4 and 8 were set for experimental comparison and verification. When the wavelet scale factor was 8, the average accuracy, average sensitivity and average specificity was 95.47%, 93.89% and 96.48%, respectively. Through comparative experiments with recent relevant literatures, the advantages of the proposed method were verified. Our results might provide reference for the clinical application of epilepsy detection.

Citation： YANG Yong, QIN Xiaolin, LIN Xiaoguang, WEN Han, PENG Yuncong. Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning. Journal of Biomedical Engineering, 2022, 39(2): 293-300. doi: 10.7507/1001-5515.202107060 Copy

1.	金洋, 张玮, 徐斌等. 发作期头皮电极脑电图在局灶性癫痫诊断中的价值. 癫痫杂志, 2019, 5(6): 431-439.
2.	杨雨时, 姚丽芬. 癫痫患者的社会认知功能: 现状与展望. 脑与神经疾病杂志, 2021, 29(7): 450-453.
3.	颜因, 彭晓燕, 王学峰. 癫痫发作后精神病的研究现状. 西南医科大学学报, 2021, 44(5): 425-428.
4.	刘晓燕. 临床脑电图学. 第2版. 北京: 人民卫生出版社, 2018: 12-33.
5.	Wang C, Zou J Z, Zhang J, et al. Recognition of epileptic EEG using support vector machines// Wang R, Gu F. Advances in Cognitive Neurodynamics (II). Dordrecht: Springer, 2009: 653-657.
6.	Chen W, Shen C P, Chiu M J, et al. Epileptic EEG visualization and sonification based on linear discriminate analysis// 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan: IEEE, 2015: 4466-4469.
7.	Sharmila A, Geethanjali P. Epileptic seizure detection from EEG signals using best feature subsets based on estimation of mutual information for support vector machines and naive bayes classifiers// International Conference on Emerging Trends and Advances in Electrical Engineering and Renewable Energy (ETAEERE). Majhitar: Sikkim Manipal Inst Technol, 2016: 585-593.
8.	Rajaguru H, Prabhakar S K. Non linear ICA and logistic regression for classification of epilepsy from EEG signals// International conference of Electronics, Communication and Aerospace Technology (ICECA). Coimbatore: IEEE, 2017: 577-580.
9.	Mursalin M, Zhang Y, Chen Y H, et al. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier. Neu Comp, 2017, 241: 204-214.
10.	Takahashi R, Matsubara T, Uehara K. Data augmentation using random image cropping and patching for deep CNNs. IEEE Trans Circuits Syst Video Technol, 2020, 30(9): 2917-2931.
11.	王芋人, 武德安. 一种提高小目标检测准确率的数据增强方法. 激光杂志, 2021, 42(11): 41-45.
12.	Wang F, Zhong S H, Peng J F, et al. Data augmentation for EEG-based emotion recognition with deep convolutional neural networks// 24th International Conference on MultiMedia Modeling(MMM). Bangkok: Chulalongkorn Univ, 2018, 10705: 82-93.
13.	Fahimi F, Dosen S, Ang K K, et al. Generative adversarial networks-based data augmentation for brain-computer interface. IEEE Trans Neural Netw Learn Syst, 2020, 32(9): 4039-4051.
14.	Krell M M, Kim S K. Rotational data augmentation for electroencephalographic data. Annu Int Conf IEEE Eng Med Biol Soc, 2017, 2017: 471-474.
15.	Wei Z, Zou J Z, Zhang J, et al. Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain. Biomedical Signal Process Control, 2019, 53: 101551.
16.	Zhang B C, Wang W N, Xiao Y T, et al. Cross-subject seizure detection in EEGs using deep transfer learning. Comput Math Methods Med, 2020, 2020: 7902072.
17.	Jiang Y Z, Wu D R, Deng Z H, et al. Seizure classification from EEG signals using transfer learning, semi-supervised learning and TSK fuzzy system. IEEE Trans Neu Syst Reh Eng, 2017, 25(12): 2270-2284.
18.	Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans Nuc Sci, 1997, 44(3): 1464-1468.
19.	王敏会, 常桂娟. 基于小波方法的时频域分析. 青岛农业大学学报, 2021, 38(3): 229-233.
20.	Akyol K. Stacking ensemble based deep neural networks modeling for effective epileptic seizure detection. Exp Syst Appl, 2020, 148: 113239.
21.	杨泽鑫. 深度集成分类模型在癫痫脑电预测中的应用研究. 太原: 太原理工大学, 2020.
22.	Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
23.	Yao X, Chen Q, Zhang G Q. Automated classification of seizures against nonseizures: A deep learning approach. arXiv, 2019: 1906.0274.
24.	Huang C B, Chen W T, Cao G T. Automatic epileptic seizure detection via attention-based CNN-BiRNN// IEEE International Conference on Bioinformatics and Biomedicine (BIBM). San Diego: IEEE, 2019: 660-663.
25.	Yao X H, Li X J, Ye Q, et al. A robust deep learning approach for automatic classification of seizures against non-seizures. Bio Sig Proc Cont, 2021, 64: 102215.

1. 金洋, 张玮, 徐斌等. 发作期头皮电极脑电图在局灶性癫痫诊断中的价值. 癫痫杂志, 2019, 5(6): 431-439.
2. 杨雨时, 姚丽芬. 癫痫患者的社会认知功能: 现状与展望. 脑与神经疾病杂志, 2021, 29(7): 450-453.
3. 颜因, 彭晓燕, 王学峰. 癫痫发作后精神病的研究现状. 西南医科大学学报, 2021, 44(5): 425-428.
4. 刘晓燕. 临床脑电图学. 第2版. 北京: 人民卫生出版社, 2018: 12-33.
5. Wang C, Zou J Z, Zhang J, et al. Recognition of epileptic EEG using support vector machines// Wang R, Gu F. Advances in Cognitive Neurodynamics (II). Dordrecht: Springer, 2009: 653-657.
6. Chen W, Shen C P, Chiu M J, et al. Epileptic EEG visualization and sonification based on linear discriminate analysis// 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan: IEEE, 2015: 4466-4469.
7. Sharmila A, Geethanjali P. Epileptic seizure detection from EEG signals using best feature subsets based on estimation of mutual information for support vector machines and naive bayes classifiers// International Conference on Emerging Trends and Advances in Electrical Engineering and Renewable Energy (ETAEERE). Majhitar: Sikkim Manipal Inst Technol, 2016: 585-593.
8. Rajaguru H, Prabhakar S K. Non linear ICA and logistic regression for classification of epilepsy from EEG signals// International conference of Electronics, Communication and Aerospace Technology (ICECA). Coimbatore: IEEE, 2017: 577-580.
9. Mursalin M, Zhang Y, Chen Y H, et al. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier. Neu Comp, 2017, 241: 204-214.
10. Takahashi R, Matsubara T, Uehara K. Data augmentation using random image cropping and patching for deep CNNs. IEEE Trans Circuits Syst Video Technol, 2020, 30(9): 2917-2931.
11. 王芋人, 武德安. 一种提高小目标检测准确率的数据增强方法. 激光杂志, 2021, 42(11): 41-45.
12. Wang F, Zhong S H, Peng J F, et al. Data augmentation for EEG-based emotion recognition with deep convolutional neural networks// 24th International Conference on MultiMedia Modeling(MMM). Bangkok: Chulalongkorn Univ, 2018, 10705: 82-93.
13. Fahimi F, Dosen S, Ang K K, et al. Generative adversarial networks-based data augmentation for brain-computer interface. IEEE Trans Neural Netw Learn Syst, 2020, 32(9): 4039-4051.
14. Krell M M, Kim S K. Rotational data augmentation for electroencephalographic data. Annu Int Conf IEEE Eng Med Biol Soc, 2017, 2017: 471-474.
15. Wei Z, Zou J Z, Zhang J, et al. Automatic epileptic EEG detection using convolutional neural network with improvements in time-domain. Biomedical Signal Process Control, 2019, 53: 101551.
16. Zhang B C, Wang W N, Xiao Y T, et al. Cross-subject seizure detection in EEGs using deep transfer learning. Comput Math Methods Med, 2020, 2020: 7902072.
17. Jiang Y Z, Wu D R, Deng Z H, et al. Seizure classification from EEG signals using transfer learning, semi-supervised learning and TSK fuzzy system. IEEE Trans Neu Syst Reh Eng, 2017, 25(12): 2270-2284.
18. Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans Nuc Sci, 1997, 44(3): 1464-1468.
19. 王敏会, 常桂娟. 基于小波方法的时频域分析. 青岛农业大学学报, 2021, 38(3): 229-233.
20. Akyol K. Stacking ensemble based deep neural networks modeling for effective epileptic seizure detection. Exp Syst Appl, 2020, 148: 113239.
21. 杨泽鑫. 深度集成分类模型在癫痫脑电预测中的应用研究. 太原: 太原理工大学, 2020.
22. Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
23. Yao X, Chen Q, Zhang G Q. Automated classification of seizures against nonseizures: A deep learning approach. arXiv, 2019: 1906.0274.
24. Huang C B, Chen W T, Cao G T. Automatic epileptic seizure detection via attention-based CNN-BiRNN// IEEE International Conference on Bioinformatics and Biomedicine (BIBM). San Diego: IEEE, 2019: 660-663.
25. Yao X H, Li X J, Ye Q, et al. A robust deep learning approach for automatic classification of seizures against non-seizures. Bio Sig Proc Cont, 2021, 64: 102215.

Journal of Biomedical Engineering

Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content