Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter December 11, 2019

Evaluation of potential auras in generalized epilepsy from EEG signals using deep convolutional neural networks and time-frequency representation

Hasan Polat EMAIL logo , Mehmet Ufuk Aluçlu and Mehmet Siraç Özerdem

Abstract

The general uncertainty of epilepsy and its unpredictable seizures often affect badly the quality of life of people exposed to this disease. There are patients who can be considered fortunate in terms of prediction of any seizures. These are patients with epileptic auras. In this study, it was aimed to evaluate pre-seizure warning symptoms of the electroencephalography (EEG) signals by a convolutional neural network (CNN) inspired by the epileptic auras defined in the medical field. In this context, one-dimensional EEG signals were transformed into a spectrogram display form in the frequency-time domain by applying a short-time Fourier transform (STFT). Systemic changes in pre-epileptic seizure have been described by applying the CNN approach to the EEG signals represented in the image form, and the subjective EEG-Aura process has been tried to be determined for each patient. Considering all patients included in the evaluation, it was determined that the 1-min interval covering the time from the second minute to the third minute before the seizure had the highest mean and the lowest variance to determine the systematic changes before the seizure. Thus, the highest performing process is described as EEG-Aura. The average success for the EEG-Aura process was 90.38 ± 6.28%, 89.78 ± 8.34% and 90.47 ± 5.95% for accuracy, specificity and sensitivity, respectively. Through the proposed model, epilepsy patients who do not respond to medical treatment methods are expected to maintain their lives in a more comfortable and integrated way.

  1. Author statement

  2. Research funding: Authors state no funding involved.

  3. Conflict of interest: Authors declare no conflict of interest.

  4. Informed Consent: Informed consent has been obtained from all patients by the Neurology Department of Dicle University.

  5. Ethical approval: The research related to human use complied with all the relevant national regulations and institutional policies and was performed in accordance with the tenets of the Helsinki Declaration, and has been approved by the authors’ institutional review board.

References

[1] Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform. J Neurosci Methods 2003;123:69–87.10.1016/S0165-0270(02)00340-0Search in Google Scholar

[2] World Health Organization. Epilepsy. [cited 2019 April 10]. Available from: http//www.who.int/mediacentre/factsheets/fs999/en/.Search in Google Scholar

[3] Fisher RS, Van Emde Boas W, Blume W, Elper C, Genton P, Lee P, et al. Epileptic seizures and epilepsy: definitions proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE). Epilepsia 2005;46:470–2.10.1111/j.0013-9580.2005.66104.xSearch in Google Scholar PubMed

[4] Nakken KO, Solaas MH, Kjeldsen MJ, Friis ML, Pellock JM, Corey LA. The occurrence and characteristics of auras in a large epilepsy cohort. Acta Neurol Scand 2009;119:88–93.10.1111/j.1600-0404.2008.01069.xSearch in Google Scholar PubMed

[5] Van Donselaar CA, Geerts AT, Schimsheimer RJ. Usefulness of an aura for classification of a first generalized seizure. Epilepsia 1990;31:529–35.10.1111/j.1528-1157.1990.tb06102.xSearch in Google Scholar PubMed

[6] Tokay T, Komsuoglu SS. Epileptic Auras. Dusunen Adam 2004;17:162–7.Search in Google Scholar

[7] Tokay T, Selekler M, Komsuoglu SS. A case with gustatory aura associated complex partial epileptic seizure. Bull Clin Psychopharmacol 2004;14:213–5.Search in Google Scholar

[8] Spencer D. Auras are frequent in patients with generalized epilepsy. Epilepsy Curr 2015;15:75–7.10.5698/1535-7597-15.2.75Search in Google Scholar PubMed PubMed Central

[9] Lohse A, Kjaer TW, Sabers A, Wolf P. Epileptic aura and perception of self-control. Epilepsy Behav 2015;45:191–4.10.1016/j.yebeh.2015.01.030Search in Google Scholar PubMed

[10] Sanei S, Chambers JA. EEG signal processing. UK: John Wiley and Sons Ltd; 2007.10.1002/9780470511923Search in Google Scholar

[11] Alkan A, Koklukaya E, Subasi A. Automatic seizure detection in EEG using logistic regression and artificial neural network. J Neurosci Methods 2005;148:167–76.10.1016/j.jneumeth.2005.04.009Search in Google Scholar PubMed

[12] Pillai J, Sperling MR. Interictal EEG and the diagnosis of epilepsy. Epilepsia 2006;47:14–22.10.1111/j.1528-1167.2006.00654.xSearch in Google Scholar PubMed

[13] Khamis H, Mohamed A, Simpson S. Frequency–moment signatures: a method for automated seizure detection from scalp EEG. Clin Neurophysiol 2013;124:2317–27.10.1016/j.clinph.2013.05.015Search in Google Scholar PubMed

[14] Nigam VP, Graupe D. A neural-network-based detection of epilepsy. Neurol Res 2004;26:55–60.10.1179/016164104773026534Search in Google Scholar

[15] Mousavi SR, Niknazar M, Vahdat BV. Epileptic seizure detection using AR model on EEG signals. CIBEC 2008;2008:1–4.10.1109/CIBEC.2008.4786067Search in Google Scholar

[16] Subasi A, Gursoy I. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 2010;37:8659–66.10.1016/j.eswa.2010.06.065Search in Google Scholar

[17] Zainuddin Z, Huong LK, Pauline O. On the use of wavelet neural networks in the task of epileptic seizure detection from electroencephalography signals. Procedia Comput Sci 2012;11:149–59.10.1016/j.procs.2012.09.016Search in Google Scholar

[18] Subaşı A, Erçelebi E. Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 2005;78:87–99.10.1016/j.cmpb.2004.10.009Search in Google Scholar

[19] Ocak H. Optimal classification of epileptic seizures in EEG using wavelet analysis and genetic algorithm. Signal Process 2008;88:1858–67.10.1016/j.sigpro.2008.01.026Search in Google Scholar

[20] Subaşı A. Signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 2007;32:1084–93.10.1016/j.eswa.2006.02.005Search in Google Scholar

[21] Yang Y, Zhou M, Niu Y, Li C, Cao R, Wang B, et al. Epileptic seizure prediction based on permutation entropy. Front Comput Neurosci 2018; 12:55.10.3389/fncom.2018.00055Search in Google Scholar

[22] Schiff SJ, Colella D, Jacyna GM, Hughes E, Creekmore JW, Marshall A, et al. Brain chirps: spectrographic signatures of epileptic seizures. Clin Neurophysiol 2000;111:953–8.10.1016/S1388-2457(00)00259-5Search in Google Scholar

[23] Netoff T, Park Y, Parhi K. Seizure prediction using cost-sensitive support vector machine. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Minneapolis, MN, USA: IEEE; 2009:3322–5.10.1109/IEMBS.2009.5333711Search in Google Scholar PubMed

[24] Park Y, Luo L, Parhi KK, Netoff T. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 2011;52:1761–70.10.1111/j.1528-1167.2011.03138.xSearch in Google Scholar PubMed

[25] Teixeira CA, Direito B, Bandarabadi M, Quyen MLV, Valderrama M, Schelter B, et al. Epileptic seizure predictors based on computational intelligence techniques: a comparative study with 278 patients. Comput Methods Programs Biomed 2017;114:324–36.10.1016/j.cmpb.2014.02.007Search in Google Scholar PubMed

[26] Mormann F, Kreuz T, Rieke C, Andrzejak RG, Kraskov A, David P, et al. On the predictability of epileptic seizures. Clin Neurophysiol 2005;116:569–87.10.1016/j.clinph.2004.08.025Search in Google Scholar PubMed

[27] Gadhoumi K, Lina JM, Gotman J. Seizure prediction in patients with mesial temporal lobe epilepsy using EEG measures of state similarity. Clin Neurophysiol 2013;124:1745–54.10.1016/j.clinph.2013.04.006Search in Google Scholar PubMed PubMed Central

[28] Chisci L, Mavino A, Perferi G, Sciandrone M, Anile C, Colicchio G, et al. Real-time epileptic seizure prediction using AR models and support vector machines. IEEE Trans Biomed Eng 2010;57:1124–32.10.1109/TBME.2009.2038990Search in Google Scholar PubMed

[29] Assi EB, Nguyen DK, Rihana S, Sawan M. Towards accurate prediction of epileptic seizures: a review. Biomed Signal Process Control 2017;34:144–57.10.1016/j.bspc.2017.02.001Search in Google Scholar

[30] Lehnertz K, Andrzejak RG, Arnhold J, Kreuz T, Mormann F, Rieke C, et al. Nonlinear EEG analysis in epilepsy: its possible use for interictal focus localization, seizure anticipation, and prevention. J Clin Neurophysiol 2001;18:209–22.10.1097/00004691-200105000-00002Search in Google Scholar PubMed

[31] Whittaker RG. Video telemetry: current concepts and recent advances. Pract Neurol 2015;15:445–50.10.1136/practneurol-2015-001216Search in Google Scholar PubMed

[32] Villanueva V, Gutierrez A, Garcia M, Beltran A, Palau J, Conde R, et al. Usefulness of video-EEG monitoring in patients with drug-resistant epilepsy. Neurologia 2011;26:6–12.10.1016/j.nrl.2010.09.029Search in Google Scholar PubMed

[33] Vale-Cardoso AS, Guimaraes HN. The effect of 50/60 Hz notch filter application on human and rat ECG recordings. Physiol Meas 2010;31:45–58.10.1088/0967-3334/31/1/004Search in Google Scholar PubMed

[34] Liu Y, Guo XM, Wu X, Li P, Wang WW. Clinical analysis of partial epilepsy with auras. Chin Med J (Engl) 2017;130:318–22.10.4103/0366-6999.198918Search in Google Scholar

[35] Zhang J, Li S, Yin Z. Pattern classification of instantaneous mental workload using ensemble of convolutional neural networks. IFAC-Papers Online 2017;50:14896–901.10.1016/j.ifacol.2017.08.2534Search in Google Scholar

[36] Yuan L, Cao J. Patients’ EEG data analysis via spectrogram image with a convolution neural network. Intell Decis Technol 2017;72:13–21.10.1007/978-3-319-59421-7_2Search in Google Scholar

[37] Guawan AAS, Surya K, Meiliana. Brainwave classification of visual stimuli based on low cost EEG spectrogram using DenseNet. Procedia Comput Sci 2018;135:128–39.10.1016/j.procs.2018.08.158Search in Google Scholar

[38] Lampert TA, O’Keefe SEM. A survey of spectrogram track detection algorithms. Appl Acoust 2010;71:87–100.10.1016/j.apacoust.2009.08.007Search in Google Scholar

[39] Başar E, Eroglu C, Karaka S, Schurmann M. Brain oscillations in perception and memory. Int J Psychophysiol 2000;35:95–124.10.1016/S0167-8760(99)00047-1Search in Google Scholar

[40] Crespel A, Gélisse P, Bureau M, Genton P. Atlas of electroencephalography. 3rd ed. Paris: J Libbey Eurotext; 2006.Search in Google Scholar

[41] Arel I, Rose D, Karnowski T. Deep machine learning – a new frontier in artificial intelligence research. IEEE Comput Intell M 2010;5:13–8.10.1109/MCI.2010.938364Search in Google Scholar

[42] Fayek HM, Margaret L, Lawrence C. Evaluating deep learning architectures for speech emotion recognition. Neural Netw 2017;92:60–8.10.1016/j.neunet.2017.02.013Search in Google Scholar PubMed

[43] Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 2017;100:270–8.10.1016/j.compbiomed.2017.09.017Search in Google Scholar PubMed

[44] Bernal J, Kushibar K, Asfaw DS, Valverde S, Oliver A, Marti R, et al. Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review. Artif Intell Med 2019;95:64–81.10.1016/j.artmed.2018.08.008Search in Google Scholar PubMed

[45] Boureau Y, Bach F, LeCun Y, Ponce J. Learning mid-level features for recognition. In: CVPR, 2010.10.1109/CVPR.2010.5539963Search in Google Scholar

[46] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436–44.10.1038/nature14539Search in Google Scholar

[47] Asadi-Pooya AA, Nei M, Sharan A, Sperling MR. Auras in patients with temporal lobe epilepsy and mesial temporal sclerosis. J Neurol Sci 2016;364:24–6.10.1016/j.jns.2016.03.006Search in Google Scholar

[48] Schulz R, Luders HO, Hoppe M, Jokeit H, Moch A, TuxhornI, et al. Lack of aura experience correlates with bitemporal dysfunction in mesial temporal lobe epilepsy. Epilepsy Res 2001;43:201–10.10.1016/S0920-1211(00)00195-9Search in Google Scholar

[49] Bianchi MT, Dworetzky BA, Bromfield EB. Auditory auras in patients with postencephalitic epilepsy: case series. Epilepsy Behav 2009;14:250–2.10.1016/j.yebeh.2008.08.008Search in Google Scholar PubMed

[50] Hatipoglu N, Bilgin G. Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships. Med Biol Eng Comput 2017;55:1829–48.10.1007/s11517-017-1630-1Search in Google Scholar PubMed

[51] Parihar AS. A study on brain tumor segmentation using convolution neural network. Inventive Computing and Informatics (ICICI). International Conference on IEEE 2017;2017:198–201.10.1109/ICICI.2017.8365336Search in Google Scholar

[52] Tan JH, Acharya UR, Bhandary SV, Chua KC, Sivaprasad S. Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. J Comput Sci 2017;20:70–9.10.1016/j.jocs.2017.02.006Search in Google Scholar

[53] Kim SK, Kang HB. An analysis of smartphone overuse recognition in terms of emotions using brainwaves and deep learning. Neurocomputing 2018;275:1393–406.10.1016/j.neucom.2017.09.081Search in Google Scholar

[54] Tabar YR, Halici U. A novel deep learning approach for classification of EEG motor imagery signals. J Neural Eng 2017;14:016003.10.1088/1741-2560/14/1/016003Search in Google Scholar PubMed

[55] Ayinala M, Parhi KK. Low complexity algorithm for seizure prediction using Adaboost. Conf Proc IEEE Eng Med Biol Soc. 2012;1061–1064.10.1109/EMBC.2012.6346117Search in Google Scholar PubMed

[56] Bandarabadi M, Teixeira CA, Rasekhi J, Dourado A. Epileptic seizure prediction using relative spectral power features. Clin Neurophysiol 2015;126:237–48.10.1016/j.clinph.2014.05.022Search in Google Scholar PubMed

[57] Abdel-Mannan O, Taylor H, Donner EJ, Sutcliffe AG. A systematic review of sudden unexpected death in epilepsy (SUDEP) in childhood. Epilepsy Behav 2019;90:99–106.10.1016/j.yebeh.2018.11.006Search in Google Scholar PubMed

[58] Tekin B. Epilepsy, pregnancy, and antiepileptic drugs. Epilepsy 2018;24:41–3.Search in Google Scholar

[59] Kwan P, Brodie MJ. Early identification of refractory epilepsy. N Eng J Med 2000;342:314–9.10.1056/NEJM200002033420503Search in Google Scholar PubMed

[60] Donner EJ, Camfield P, Brooks L, Buchhalter J, Camfield C, Loddenkemper T, et al. Understanding death in children with epilepsy. Pediatr Neurol 2017;70:7–15.10.1016/j.pediatrneurol.2017.01.011Search in Google Scholar PubMed

[61] Manolis TA, Manolis AA, Melita H, Manolis AS. Sudden unexpected death in epilepsy: the neuro-cardio-respiratory connection. Seizure 2018;64:65–73.10.1016/j.seizure.2018.12.007Search in Google Scholar PubMed

Received: 2019-04-27
Accepted: 2019-10-07
Published Online: 2019-12-11
Published in Print: 2020-08-27

©2019 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 27.1.2023 from https://www.degruyter.com/document/doi/10.1515/bmt-2019-0098/html
Scroll Up Arrow