A model based on the graph attention network for epileptic seizure anomaly detection_Journal of Biomedical Engineering

Authors：

LIANG Guohua ¹ , E Jina ¹ , LI Hanyi ¹ , FANG Zhiwen ¹ , WANG Jun ² , ZHAN Chang’an ¹ ,  YANG Feng ¹

1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, P. R. China;
2. Neurosurgery Center, Zhujiang Hospital of Southern Medical University, Guangzhou 510280, P. R. China;

Corresponding author：

YANG Feng, Email: yangf@smu.edu.cn

Keywords：

Electroencephalogram; Anomaly detection; Graph attention network; Deep learning; Seizure detection

DOI：

10.7507/1001-5515.202411002

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The existing epilepsy seizure detection algorithms have problems such as overfitting and poor generalization ability due to high reliance on manual labeling of electroencephalogram’s data and data imbalance between seizure and interictal periods. An unsupervised learning detection method for epileptic seizure that jointed graph attention network (GAT) and Transformer framework (GAT-T) was proposed. In this method, channel correlations were adaptively learned by GAT encoder. Temporal information was captured by one-dimensional convolution decoder. Combining outputs of the two mentioned above, predicted values for electroencephalogram were generated. The collective anomaly score was calculated and the detection threshold was determined. The results demonstrated that GAT-T achieved the average performance exceeding 90% (or 99%) with a 0.25 s (or 2 s) time segment length, which could effectively detect epileptic seizures. Moreover, the channel association probability matrix was expected to assist clinicians in the initial screening of the epileptogenic zone, and ablation experiments also reflected the significance of each module in GAT-T. This study may assist clinicians in making more accurate diagnostic and therapeutic decisions for epilepsy patients.

Citation： LIANG Guohua, E Jina, LI Hanyi, FANG Zhiwen, WANG Jun, ZHAN Chang’an, YANG Feng. A model based on the graph attention network for epileptic seizure anomaly detection. Journal of Biomedical Engineering, 2025, 42(4): 693-700. doi: 10.7507/1001-5515.202411002 Copy

1.	Fiest K M, Sauro K M, Wiebe S, et al. Prevalence and incidence of epilepsy: a systematic review and meta-analysis of international studies. Neurology, 2017, 88(3): 296-303.
2.	Palak H, Lavanya, Nidhi G, et al. Software advancements in automatic epilepsy diagnosis and seizure detection: 10-year review. Artif Intell Rev, 2024, 57(7): 181.
3.	Pressler R M, Cilio M R, Mizrahi E M, et al. The ILAE classification of seizures and the epilepsies: modification for seizures in the neonate. Position paper by the ILAE task force on neonatal seizures. Epilepsia, 2021, 62(3): 615-628.
4.	Si Yang. Machine learning applications for electroencephalograph signals in epilepsy: a quick review. Acta Epileptol, 2020, 2(1): 5.
5.	Li Yang, Yang Yang, Zheng Qinghe, et al. Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG. Med Biol Eng Comput, 2024, 62(1): 307-326.
6.	Alqirshi R, Belhaouari S B. EEG-based patient independent epileptic seizure detection using GCN-BRF// International Conference on Deep Learning Theory and Applications (DELTA). Dijon: SNS, 2024: 351-366.
7.	Wu Guanlin, Yu Ke, Zhou Hao, et al. Time-series anomaly detection based on dynamic temporal graph convolutional network for epilepsy diagnosis. Bioengineering, 2024, 11(1): 53.
8.	王兴起, 李明爱. 应用基于注意力的多尺度残差网络实现癫痫脑电自动检测. 生物医学工程学杂志, 2024, 41(2): 253-261.
9.	Karpov E O, Khoymov S M, Maksimenko A V, et al. Evaluation of unsupervised anomaly detection techniques in labelling epileptic seizures on human EEG. Appl Sci, 2023, 13(9): 5655.
10.	Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. J Neur Eng, 2019, 16(5): 051001.
11.	刘晓辰. 基于机器学习的癫痫脑电处理及应用研究. 杭州: 浙江大学, 2021.
12.	Li Hanyi, Liao Jiahui, Wang Hongxiao, et al. EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction. Comput Biol Med, 2024, 175: 108510.
13.	de Albuquerque Filho J E, Brandão L C P, Fernandes B J T, et al. A review of neural networks for anomaly detection. IEEE Access, 2022, 10: 112342-112367.
14.	Zamanzadeh Darban Z, Webb G I, Pan S, et al. Deep learning for time series anomaly detection: a survey. ACM Comput Surv, 2024, 57(1): 1-42.
15.	You S, Cho B H, Yook S, et al. Unsupervised automatic seizure detection for focal-onset seizures recorded with behind-the-ear EEG using an anomaly-detecting generative adversarial network. Comput Meth Progr Biomed, 2020, 193: 105472.
16.	You S, Cho B H, Shon Y M, et al. Semi-supervised automatic seizure detection using personalized anomaly detecting variational autoencoder with behind-the-ear EEG. Comput Meth Progr Biomed, 2022, 213: 106542.
17.	欧嘉志, 詹长安, 杨丰. 一维卷积神经网络的自编码癫痫发作异常检测模型. 南方医科大学学报, 2024, 44(9): 1796-1804.
18.	Xu Jiehui, Wu Haixu, Wang Jianmin, et al. Anomaly Transformer: time series anomaly detection with association discrepancy// International Conference on Learning Representations (ICLR). Online: IMLS, 2022.
19.	Chen Wenchao, Tian Long, Chen Bo, et al. Deep variational graph convolutional recurrent network for multivariate time series anomaly detection// International Conference on Machine Learning (ICML). Baltimore: IMLS, 2022: 3621-3633.
20.	Zhao Mengmeng, Peng Haipeng, Li Lixiang, et al. Graph attention network and informer for multivariate time series anomaly detection. Sensors, 2024, 24(5): 1522.
21.	Deng A, Hooi B. Graph neural network-based anomaly detection in multivariate time series// Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). Beijing: AAAI, 2021: 4027-4035.
22.	Chen Zekai, Chen Dingshuo, Zhang Xiao, et al. Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Intern Things J, 2021, 9(12): 9179-9189.
23.	Siletti K, Hodge R, Mossi Albiach A, et al. Transcriptomic diversity of cell types across the adult human brain. Science, 2023, 382(6667): eadd7046.
24.	Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment. Cambridge: Massachusetts Institute of Technology, 2009.
25.	Zhang Yuan, Guo Yao, Yang Po, et al. Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network. IEEE J Biomed Health Inform, 2019, 24(2): 465-474.
26.	Detti P, Vatti G, Zabalo Manrique de Lara G. EEG synchronization analysis for seizure prediction: a study on data of noninvasive recordings. Processes, 2020, 8(7): 846.
27.	Fey M, Lenssen E J. Fast graph representation learning with pytorch geometric. arXiv, 2019: 1903.02428.
28.	Babaeeghazvini P, Rueda-Delgado L M, Gooijers J, et al. Brain structural and functional connectivity: a review of combined works of diffusion magnetic resonance imaging and electro-encephalography. Front Hum Neurosci, 2021, 15: 721206.

1. Fiest K M, Sauro K M, Wiebe S, et al. Prevalence and incidence of epilepsy: a systematic review and meta-analysis of international studies. Neurology, 2017, 88(3): 296-303.
2. Palak H, Lavanya, Nidhi G, et al. Software advancements in automatic epilepsy diagnosis and seizure detection: 10-year review. Artif Intell Rev, 2024, 57(7): 181.
3. Pressler R M, Cilio M R, Mizrahi E M, et al. The ILAE classification of seizures and the epilepsies: modification for seizures in the neonate. Position paper by the ILAE task force on neonatal seizures. Epilepsia, 2021, 62(3): 615-628.
4. Si Yang. Machine learning applications for electroencephalograph signals in epilepsy: a quick review. Acta Epileptol, 2020, 2(1): 5.
5. Li Yang, Yang Yang, Zheng Qinghe, et al. Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG. Med Biol Eng Comput, 2024, 62(1): 307-326.
6. Alqirshi R, Belhaouari S B. EEG-based patient independent epileptic seizure detection using GCN-BRF// International Conference on Deep Learning Theory and Applications (DELTA). Dijon: SNS, 2024: 351-366.
7. Wu Guanlin, Yu Ke, Zhou Hao, et al. Time-series anomaly detection based on dynamic temporal graph convolutional network for epilepsy diagnosis. Bioengineering, 2024, 11(1): 53.
8. 王兴起, 李明爱. 应用基于注意力的多尺度残差网络实现癫痫脑电自动检测. 生物医学工程学杂志, 2024, 41(2): 253-261.
9. Karpov E O, Khoymov S M, Maksimenko A V, et al. Evaluation of unsupervised anomaly detection techniques in labelling epileptic seizures on human EEG. Appl Sci, 2023, 13(9): 5655.
10. Roy Y, Banville H, Albuquerque I, et al. Deep learning-based electroencephalography analysis: a systematic review. J Neur Eng, 2019, 16(5): 051001.
11. 刘晓辰. 基于机器学习的癫痫脑电处理及应用研究. 杭州: 浙江大学, 2021.
12. Li Hanyi, Liao Jiahui, Wang Hongxiao, et al. EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction. Comput Biol Med, 2024, 175: 108510.
13. de Albuquerque Filho J E, Brandão L C P, Fernandes B J T, et al. A review of neural networks for anomaly detection. IEEE Access, 2022, 10: 112342-112367.
14. Zamanzadeh Darban Z, Webb G I, Pan S, et al. Deep learning for time series anomaly detection: a survey. ACM Comput Surv, 2024, 57(1): 1-42.
15. You S, Cho B H, Yook S, et al. Unsupervised automatic seizure detection for focal-onset seizures recorded with behind-the-ear EEG using an anomaly-detecting generative adversarial network. Comput Meth Progr Biomed, 2020, 193: 105472.
16. You S, Cho B H, Shon Y M, et al. Semi-supervised automatic seizure detection using personalized anomaly detecting variational autoencoder with behind-the-ear EEG. Comput Meth Progr Biomed, 2022, 213: 106542.
17. 欧嘉志, 詹长安, 杨丰. 一维卷积神经网络的自编码癫痫发作异常检测模型. 南方医科大学学报, 2024, 44(9): 1796-1804.
18. Xu Jiehui, Wu Haixu, Wang Jianmin, et al. Anomaly Transformer: time series anomaly detection with association discrepancy// International Conference on Learning Representations (ICLR). Online: IMLS, 2022.
19. Chen Wenchao, Tian Long, Chen Bo, et al. Deep variational graph convolutional recurrent network for multivariate time series anomaly detection// International Conference on Machine Learning (ICML). Baltimore: IMLS, 2022: 3621-3633.
20. Zhao Mengmeng, Peng Haipeng, Li Lixiang, et al. Graph attention network and informer for multivariate time series anomaly detection. Sensors, 2024, 24(5): 1522.
21. Deng A, Hooi B. Graph neural network-based anomaly detection in multivariate time series// Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). Beijing: AAAI, 2021: 4027-4035.
22. Chen Zekai, Chen Dingshuo, Zhang Xiao, et al. Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Intern Things J, 2021, 9(12): 9179-9189.
23. Siletti K, Hodge R, Mossi Albiach A, et al. Transcriptomic diversity of cell types across the adult human brain. Science, 2023, 382(6667): eadd7046.
24. Shoeb A H. Application of machine learning to epileptic seizure onset detection and treatment. Cambridge: Massachusetts Institute of Technology, 2009.
25. Zhang Yuan, Guo Yao, Yang Po, et al. Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network. IEEE J Biomed Health Inform, 2019, 24(2): 465-474.
26. Detti P, Vatti G, Zabalo Manrique de Lara G. EEG synchronization analysis for seizure prediction: a study on data of noninvasive recordings. Processes, 2020, 8(7): 846.
27. Fey M, Lenssen E J. Fast graph representation learning with pytorch geometric. arXiv, 2019: 1903.02428.
28. Babaeeghazvini P, Rueda-Delgado L M, Gooijers J, et al. Brain structural and functional connectivity: a review of combined works of diffusion magnetic resonance imaging and electro-encephalography. Front Hum Neurosci, 2021, 15: 721206.

Journal of Biomedical Engineering

A model based on the graph attention network for epileptic seizure anomaly detection

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content