Skip to main content

Advertisement

Springer Nature Link
Log in

A channel-wise attention-based representation learning method for epileptic seizure detection and type classification

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Epilepsy affect almost 1% of the worldwide population. An early diagnosis of seizure types is a crucial patient-dependent step for the treatment selection process. The selection of the proper treatment relies on the correct identification of the seizure type. As such, identifying the seizure type has the biggest immediate influence on therapy than the seizure detection, reducing the neurologist’s efforts when reading and detecting seizures in EEG recordings. Most of the existing seizure detection and classification methods are conceptualized following the patient-dependent schema thus fail to perform well with unknown cases. Our work focuses on patient-independent schema for seizure type classification and pays more attention to the explainability of the underlying attention mechanism of our method. Using a channel-wise attention mechanism, a quantification of the EEG channels contribution is enabled. Therefore, results become more interpretable and a visualization of brain lobes contribution by seizure types is allowed. We evaluate our model for seizure detection and type classification on CHB-MIT and the recently released TUH EEG Seizure, respectively. Our model is able to classify 8 seizure types with an accuracy of 98.41%, directly from raw EEG data without any preprocessing. A case study showed a high correlation between the neurological baselines and the interpretable results of our model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Notes

  1. The PrePrint version was published on the TechRxiv server: https://doi.org/10.36227/techrxiv.17087147.v1Baghdadi et al. (2023).

References

  • Abbasi MU, Rashad A, Basalamah A, Tariq M (2019) Detection of epilepsy seizures in neo-natal eeg using lstm architecture. IEEE Access 7:179074

    Article  Google Scholar 

  • Ahmedt-Aristizabal D, Fernando T, Denman S, Petersson L, Aburn MJ, Fookes C (2019) Neural memory networks for robust classification of seizure type. arXiv:1912.04968

  • Asif U, Roy S, Tang J, Harrer S (2020) Seizurenet: multi-spectral deep feature learning for seizure type classification. In: Machine learning in clinical neuroimaging and radiogenomics in neuro-oncology

  • Baghdadi A, Fourati R, Aribi Y, Daoud S, Dammak M, Mhiri C, Chabchoub H, Siarry P, Alimi A (2023) A channel-wise attention-based representation learning method for epileptic seizure detection and type classification. Preprint on TechRxiv,2023. https://doi.org/10.36227/techrxiv.17087147.v1

  • Baghdadi A, Aribi Y, Fourati R, Halouani N, Siarry P, Alimi A (2020a) Psychological stimulation for anxious states detection based on eeg-related features. J Ambient Intell Humaniz Comput 1

  • Baghdadi A, Fourati R, Aribi Y, Siarry P, Alimi AM (2020b) Robust feature learning method for epileptic seizures prediction based on long-term eeg signals. In: 2020 international joint conference on neural networks (IJCNN), p 1. IEEE

  • Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, San Diego, May 7–9, 2015, Conference Track Proceedings

  • Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua T (2017) Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning, p 6298

  • Cimr D, Fujita H, Tomaskova H, Cimler R, Selamat A (2022) Automatic seizure detection by convolutional neural networks with computational complexity analysis. Comput Methods Progr Biomed. https://doi.org/10.1016/j.cmpb.2022.107277

    Article  Google Scholar 

  • Cisotto G, Zanga A, Chlebus J, Zoppis I, Manzoni S, Markowska-Kaczmar U (2020) Comparison of attention-based deep learning models for eeg classification. arXiv:2012.01074

  • Craik A, He Y, Contreras-Vidal JL (2019) Deep learning for electroencephalogram (eeg) classification tasks: a review. J Neural Eng 16(3):031001

    Article  Google Scholar 

  • Eom H, Lee D, Han S, Hariyani YS, Lim Y, Sohn I, Park K, Park C (2020) End-to-end deep learning architecture for continuous blood pressure estimation using attention mechanism. Sensors 20(8):2338

    Article  Google Scholar 

  • Fourati R, Ammar B, Aouiti C, Sanchez-Medina J, Alimi AM (2017) Optimized echo state network with intrinsic plasticity for eeg-based emotion recognition. In: International conference on neural information processing, p 718. Springer

  • Fourati R, Ammar B, Jin Y, Alimi AM (2020a) Eeg feature learning with intrinsic plasticity based deep echo state network. In: 2020 international joint conference on neural networks (IJCNN), p 1. IEEE

  • Fourati R, Ammar B, Sanchez-Medina J, Alimi AM (2020b) Unsupervised learning in reservoir computing for eeg-based emotion recognition. IEEE Trans Affect Comput. https://doi.org/10.1109/TAFFC.2020.2982143

    Article  Google Scholar 

  • Gao X, Zhu Y, Yang Y, Zhang F, Zhou F, Tian X, Xu K, Chen Y (2022) A seizure detection method based on hypergraph features and machine learning. Biomed Signal Process Control 77:103769. https://doi.org/10.1016/j.bspc.2022.103769

    Article  Google Scholar 

  • Goldenberg MM (2010) Overview of drugs used for epilepsy and seizures: etiology, diagnosis, and treatment. Pharm Ther 35(7):392

    Google Scholar 

  • Harati A, Lopez S, Obeid I, Picone J, Jacobson M, Tobochnik S (2014) The tuh eeg corpus: a big data resource for automated eeg interpretation. In: 2014 IEEE signal processing in medicine and biology symposium (SPMB), p 1. IEEE

  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735

    Article  Google Scholar 

  • Hu H, Li Q, Zhao Y, Zhang Y (2020) Parallel deep learning algorithms with hybrid attention mechanism for image segmentation of lung tumors. IEEE Trans Ind Inf 17(4):2880

    Article  Google Scholar 

  • Jiang L, He J, Pan H, Wu D, Jiang T, Liu J (2023) Seizure detection algorithm based on improved functional brain network structure feature extraction. Biomed Signal Process Control 79:104053. https://doi.org/10.1016/j.bspc.2022.104053

    Article  Google Scholar 

  • Kaushik P, Gupta A, Roy PP, Dogra DP (2018) Eeg-based age and gender prediction using deep blstm-lstm network model. IEEE Sens J 19(7):2634

    Article  Google Scholar 

  • Lerche H, Shah M, Beck H, Noebels J, Johnston D, Vincent A (2013) Ion channels in genetic and acquired forms of epilepsy. J Physiol 591(4):753

    Article  Google Scholar 

  • Leske S, Dalal SS (2019) Reducing power line noise in eeg and meg data via spectrum interpolation. Neuroimage 189:763

    Article  Google Scholar 

  • Li Y, Zheng W, Wang L, Zong Y, Cui Z (2019) From regional to global brain: a novel hierarchical spatial-temporal neural network model for eeg emotion recognition. IEEE Trans Affect Comput. https://doi.org/10.1109/TAFFC.2019.2922912

    Article  Google Scholar 

  • Liu T, Truong ND, Nikpour A, Zhou L, Kavehei O (2020) Epileptic seizure classification with symmetric and hybrid bilinear models. IEEE J Biomed Health Inform 24(10):2844

    Article  Google Scholar 

  • Miao Y, Gowayyed M, Metze F (2015) Eesen: end-to-end speech recognition using deep rnn models and wfst-based decoding. In: 2015 IEEE workshop on automatic speech recognition and understanding (ASRU), p 167. IEEE

  • Nahmias DO, Civillico EF, Kontson KL (2020) Deep learning and feature based medication classifications from eeg in a large clinical data set. Sci Rep 10(1):1

    Article  Google Scholar 

  • Panayiotopoulos C (2005a) Clinical aspects of the diagnosis of epileptic seizures and epileptic syndromes. In: The epilepsies: seizures, syndromes and management. Bladon Medical Publishing

  • Panayiotopoulos C (2005b) Optimal use of the eeg in the diagnosis and management of epilepsies. In: The epilepsies: seizures, syndromes and management. Bladon Medical Publishing

  • Roy S, Asif U, Tang J, Harrer S (2019) Machine learning for seizure type classification: setting the benchmark. arXiv:1902.01012

  • Saputro IRD, Maryati ND, Solihati SR, Wijayanto I, Hadiyoso S, Patmasari R (2019) Seizure type classification on eeg signal using support vector machine. J Phys Conf Ser 1201:012065

    Article  Google Scholar 

  • Shah V, Von Weltin E, Lopez S, McHugh JR, Veloso L, Golmohammadi M, Obeid I, Picone J (2018) The temple university hospital seizure detection corpus. Front Neuroinform 12:83

    Article  Google Scholar 

  • Shen M, Wen P, Song B, Li Y (2022) An eeg based real-time epilepsy seizure detection approach using discrete wavelet transform and machine learning methods. Biomed Signal Process Control 77:103820. https://doi.org/10.1016/j.bspc.2022.103820

    Article  Google Scholar 

  • Shoeb AH (2009) Application of machine learning to epileptic seizure onset detection and treatment. PhD thesis, Massachusetts Institute of Technology

  • Sriraam N, Temel Y, Rao SV, Kubben PL (2019) A convolutional neural network based framework for classification of seizure types. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), p 2547. IEEE

  • Tang F-G, Liu Y, Li Y, Peng Z-W (2020) A unified multi-level spectral-temporal feature learning framework for patient-specific seizure onset detection in eeg signals. Knowl Based Syst 205:106152

    Article  Google Scholar 

  • Temko A, Lightbody G, Thomas EM, Boylan GB, Marnane W (2011) Instantaneous measure of eeg channel importance for improved patient-adaptive neonatal seizure detection. IEEE Trans Biomed Eng 59(3):717

    Article  Google Scholar 

  • Tsiouris KM, Pezoulas VC, Zervakis M, Konitsiotis S, Koutsouris DD, Fotiadis DI (2018) A long short-term memory deep learning network for the prediction of epileptic seizures using eeg signals. Comput Biol Med 99:24

    Article  Google Scholar 

  • Yao X, Li X, Ye Q, Huang Y, Cheng Q, Zhang G-Q (2021) A robust deep learning approach for automatic classification of seizures against non-seizures. Biomed Signal Process Control 64:102215

    Article  Google Scholar 

  • Yin W, Kann K, Yu M, Schütze H (2017) Comparative study of cnn and rnn for natural language processing. arXiv:1702.01923

  • Yuan Y, Jia K (2019) Fusionatt: deep fusional attention networks for multi-channel biomedical signals. Sensors 19(11):2429

    Article  Google Scholar 

  • Yuan Y, Xun G, Jia K, Zhang A (2018a) A multi-view deep learning framework for eeg seizure detection. IEEE J Biomed Health Inform 23(1):83

    Article  Google Scholar 

  • Yuan Y, Xun G, Ma F, Suo Q, Xue H, Jia K, Zhang A (2018b) A novel channel-aware attention framework for multi-channel eeg seizure detection via multi-view deep learning. In: 2018 IEEE EMBS international conference on biomedical & health informatics (BHI), p 206. IEEE

  • Zhang X, Yao L, Dong M, Liu Z, Zhang Y, Li Y (2020) Adversarial representation learning for robust patient-independent epileptic seizure detection. IEEE J Biomed Health Inform 24(10):2852–9

    Article  Google Scholar 

Download references

Acknowledgements

The research leading to these results has received funding from the Ministry of Higher Education and Scientific Research of Tunisia under the Grant Agreement Number LR11ES48.

Author information

Authors and Affiliations

  1. Esprit School of Business, Computer Science and Applied Mathematics Department, Tunis, Tunisia

    Asma Baghdadi

  2. Research Groups in Intelligent Machines, National Engineering School of Sfax (ENIS), University of Sfax, BP 1173, 3038, Sfax, Tunisia

    Asma Baghdadi, Rahma Fourati & Adel Alimi

  3. Laboratoire Images, Signaux et Systèmes Intelligents, Université Paris Est Créteil, 120 Rue Paul Armangot, 94400, Vitry sur Seine, France

    Asma Baghdadi & Patrick Siarry

  4. Faculty of Law, Economics and Management Sciences of Jendouba (FSJEGJ), University of Jendouba, Jendouba, Tunisia

    Rahma Fourati

  5. Sciences and Technology Department, University College of Ranyah Taif University, Taif, Saudi Arabia

    Yassine Aribi

  6. Department of Neurology, Habib Bourguiba University Hospital, Sfax, Tunisia

    Sawsen Daoud, Mariem Dammak & Chokri Mhiri

  7. Neuroscience Laboratory, Sfax university, LR-12-SP-19, Sfax, Tunisia

    Sawsen Daoud, Mariem Dammak & Chokri Mhiri

  8. College of Business, Al Ain University, Abu Dhabi, United Arab Emirates

    Habib Chabchoub

  9. LiSSi, Université de Paris 12, 94010, Créteil, France

    Patrick Siarry

  10. Department of Electrical and Electronic Engineering Science, Faculty of Engineering and the Built Environment, University of Johannesburg, Johannesburg, South Africa

    Adel Alimi

Authors
  1. Asma Baghdadi
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Rahma Fourati
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yassine Aribi
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Sawsen Daoud
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Mariem Dammak
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Chokri Mhiri
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Habib Chabchoub
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Patrick Siarry
    View author publications

    You can also search for this author inPubMed Google Scholar

  9. Adel Alimi
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Asma Baghdadi or Rahma Fourati.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Baghdadi, A., Fourati, R., Aribi, Y. et al. A channel-wise attention-based representation learning method for epileptic seizure detection and type classification. J Ambient Intell Human Comput 14, 9403–9418 (2023). https://doi.org/10.1007/s12652-023-04609-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-023-04609-6

Keywords