Fast statistical model-based classification of epileptic EEG signals

• Autorzy: Quintero-Rincón A. , Pereyra M. , D'Giano C. , Risk M. , Batatia H.

Identyfikatory

DOI

10.1016/j.bbe.2018.08.002

• Języki publikacji: EN

Abstrakty

EN

This paper presents a supervised classification method to accurately detect epileptic brain activity in real-time from electroencephalography (EEG) data. The proposed method has three main strengths: it has low computational cost, making it suitable for real-time implementation in EEG devices; it performs detection separately for each brain rhythm or EEG spectral band, following the current medical practices; and it can be trained with small datasets, which is key in clinical problems where there is limited annotated data available. This is in sharp contrast with modern approaches based on machine learning techniques, which achieve very high sensitivity and specificity but require large training sets with expert annotations that may not be available. The proposed method proceeds by first separating EEG signals into their five brain rhythms by using awavelet filter bank. Each brain rhythm signal is then mapped to a low-dimensional manifold by using a generalized Gaussian statistical model; this dimensionality reduction step is computationally straight-forward and greatly improves supervised classification performance in problems with little training data available. Finally, this is followed by parallel linear classifications on the statistical manifold to detect if the signals exhibit healthy or abnormal brain activity in each spectral band. The good performance of the proposed method is demonstrated with an application to paediatric neurology using 39 EEG recordings from the Children's Hospital Boston database, where it achieves an average sensitivity of 98%, specificity of 88%, and detection latency of 4 s, performing similarly to the best approaches from the literature.

Słowa kluczowe

EN

generalized Gaussian distribution; wavelet filter bank; electroencephalography; epilepsy; leave one out cross validation; linear classifier

PL

rozkład Gaussiana; elektroencefalografia; epilepsja; klasyfikator liniowy

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2018
• Tom: Vol. 38, no. 4
• Strony: 877--889
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Quintero-Rincón A.

• Department of Bioengineering, Instituto Tecnológico de Buenos Aires (ITBA), Av. Eduardo Madero 399, C1106ACD Buenos Aires, Argentina

autor

Pereyra M.

• School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, UK

autor

D'Giano C.

• Centro Integral de Epilepsia y Telemetría, Fundación Lucha contra las Enfermedades Neurológicas Infantiles (FLENI), Buenos Aires, Argentina

autor

Risk M.

• Department of Bioengineering, Instituto Tecnológico de Buenos Aires (ITBA), Buenos Aires, Argentina; Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina

autor

Batatia H.

• University of Toulouse, IRIT – INPT, Toulouse, France

Bibliografia

• [1] Parker JN, Parker PM. The official patient's sourcebook on seizures and epilepsy. The MIT Press; 2003.
• [2] Smithson WH, Walker MC. ABC of epilepsy. BMJ Books; 2012.
• [3] Fisher RS, Acevedo C, Arzimanoglou A, Bogacz A, Cross JH, Elger CE, et al. Ilae official report: a practical clinical definition of epilepsy. Epilepsy 2014;55(4):475–82.
• [4] Viglione S, Ordon V, Risch F. A methodology for detecting ongoing changes in the eeg prior to clinical seizures. 21st Western Institute on Epilepsy; 2011.
• [5] Liss S, Apparatus for monitoring and counteracting excess brain electrical energy to prevent epileptic seizures and the like, US patent No. 3850161.
• [6] Ktonas P, Smith J. Quantification of abnormal eeg spike characteristics. Comput Biol Med 1974;4(2):157–63.
• [7] Gotman J, Ives J, Gloor P. Automatic recognition of interictal epileptic activity in prolonged eeg recordings. Electroencephalogr Clin Neurophysiol 1979;46(5):510–20.
• [8] Iasemidis LD, Zaveri HP, Sackellares JC, Williams WJ. Linear and nonlinear modeling of ECoG in temporal lobe epilepsy. 25th Annual Rocky Mountain Bioengineering Symposium; 1988.
• [9] Iasemidis LD, Zaveri HP, Sackellares JC, Williams WJ. Nonlinear dynamics of electrocorticographic data. J Clin Neurophysiol 2006;5(339).
• [10] Sorensen TL, Olsen UL, Conradsen I, Henriksen J, Kjaer TW, Thomsen CE, et al. Automatic epileptic seizure onset detection using matching pursuit: a case study. 32nd Annual International Conference of the IEEE EMB. 2010. pp. 3277–80.
• [11] Liang S-F, Wang H-C, Chang W-L. Combination of eeg complexity and spectral analysis for epilepsy diagnosis and seizure detection. EURASIP J Adv Signal Process 2010; 2010(1):853434.
• [12] Bajaj V, Pachori RB. Classification of seizure and nonseizure eeg signals using empirical mode decomposition. IEEE Trans Inf Technol BioMed 2012;16(6):1135–42.
• [13] Nasehi S, PourghassemH. A novel fast epileptic seizure onset detection algorithm using general tensor discriminant analysis. J Clin Neurophysiol 2013;30(4):362–70.
• [14] Shoeb A, Edwards H, Connolly J, Bourgeois B, Treves ST, Guttagf J. Patient-specific seizure onset detection. Epilepsy Behav 2004;5:483–98.
• [15] Meng L, Frei MG, Osorio I, Strang G, Nguyen TQ. Gaussian mixture models of ecog signal features for improved detection of epileptic seizures. Med Eng Phys 2004;26 (5):379–93.
• [16] Chan A, Sun F, Boto E, Wingeier B. Automated seizure onset detection for accurate onset time determination in intracranial eeg. Clin Neurophysiol 2008;119(12):2687–96.
• [17] Ocak H. Automatic detection of epileptic seizures in eeg using discrete wavelet transform and approximate entropy. Expert Syst Appl 2009;36:2027–36.
• [18] Rabbi AF, Fazel-Rezai R. A fuzzy logic system for seizure onset detection in intracranial eeg. Comput Intell Neurosci 2012;2012:705140.
• [19] Direito B, Teixeira C, Ribeiro B, Castelo-Branco M, Sales F, Dourado A. Modeling epileptic brain states using eeg spectral analysis and topographic mapping. J Neurosci Methods 2012;210(2):220–9.
• [20] Pachori RB. Discrimination between ictal and seizure-free eeg signals using empirical mode decomposition. Res Lett Signal Process 2008. 293056.
• [21] BilasPachori R, Bajaj V. Analysis of normal and epileptic seizure eeg signals using empirical mode decomposition. Comput Methods Prog Biomed 2011;104(3):373–81.
• [22] Pachori RB, Patidar S. Epileptic seizure classification in eeg signals using second-order difference plot of intrinsic mode functions. Comput Methods Prog Biomed 2014;113 (2):494–502.
• [23] Supratak A, Li L, Guo Y. Feature extraction with stacked autoencoders for epileptic seizure detection. Eng Med Biol Soc (EMBC) 2014.
• [24] Swami P, Gandhi TK, Panigrahi BK, Tripathi M, Anand S. A novel robust diagnostic model to detect seizures in electroencephalography. Expert Syst Appl 2016;56:116–30.
• [25] Bhati D, Pachori RB, Gadre VM. A novel approach for time-frequency localization of scaling functions and design of three-band biorthogonal linear phase wavelet filter banks. Digit Signal Process 2017;69:309–22.
• [26] Qaraqe M, Ismail M, Serpedin E. Band-sensitive seizure onset detection via csp-enhanced eeg features. Epilepsy Behav 2015;50:77–87.
• [27] Acharya U, Oh SL, Hagiwara Y, Tan J, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using eeg signals. Comput Biol Med 2017;17:1–9.
• [28] Hosseini M, Pompili D, Elisevich K, Soltanian-Zadeh H. Random ensemble learning for eeg classification. Artif Intell Med 2018;17(S0933-3657):30201–4.
• [29] Logesparan L, Rodriguez-Villegas E, Casson A. The impact of signal normalization on seizure detection using line length features. Med Biol Eng Comput 2015;53(10):929–42.
• [30] Bhattacharyya A, Pachori RB, Upadhyay A, Acharya UR. Tunable-q wavelet transform based multiscale entropy measure for automated classification of epileptic eeg signals. Appl Sci 2017;7(4):385.
• [31] Bhattacharyya A, Pachori RB, Acharya UR. Tunable-q wavelet transform based multivariate sub-band entropy with application to focal eeg signal analysis. Entropy 2017;19(3):99.
• [32] Sharma RR, Pachori RB. A novel approach to detect epileptic seizures using a combination of tunable-q wavelet transform and fractal dimension. J Mech Med Biol 2017;17(17):2017.
• [33] Sharma M, Pachori RB, Acharya UR. A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension. Pattern Recogn Lett 2017;94:172–9.
• [34] Fraley C, Raftery AE. Model-based methods of classification: using the mclust software in chemometrics. J Stat Plan Inference 2007;18(6):1–13.
• [35] McNicholas P. Model-based classification using latent gaussian mixture models. J Stat Plan Inference 2010;140 (5):1175–81.
• [36] Saez A, Serrano C, Acha B. Model-based classification methods of global patterns in dermoscopic images. IEEE Trans Med Imaging 2014;33(5):1137–47.
• [37] Luessi M, Babacan S, Molina R, Booth J, Katsaggelos A. Bayesian symmetrical eeg/fmri fusion with spatially adaptive priors. NeuroImage 2011;55(1):113–32.
• [38] Cortés J, López A, Molina R, Katsaggelos A. Variational bayesian localization of eeg sources with generalized gaussian priors. Eur Phys J-Plus (EPJP) 2012;127(140):12140–9.
• [39] EPILEPSIAE. Epilepsiae epilepsy project; 2018, http://www.epilepsiae.eu/ [accessed 02.02.18].
• [40] krishnan B, Vlachos I, Faith A, Mullane S, Williams K, Alexopoulos A, et al. A novel spatiotemporal analysis of peri-ictal spiking to probe the relation of spikes and seizures in epilepsy. Ann Biomed Eng 2014;42(8):1606–17.
• [41] Joshi V, Pachori RB, Vijesh A. Classification of ictal and seizure-free eeg signals using fractional linear prediction. Biomed Signal Process Control 2014;9:1–5.
• [42] Sharma RR, Pachori RB. Classification of epileptic seizures in eeg signals based on phase space representation of intrinsic mode functions. Expert Syst Appl 2015;42(3):1106–17.
• [43] Zheng Y, Zhu J, Qi Y, Zheng X, Zhang J. An automatic patient-specific seizure onset detection method using intracranial electroencephalography. Neuromodulation 2015;18(2):79–84.
• [44] Kumar TS, Kanhanga V, Pachori RB. Classification of seizure and seizure-free eeg signals using local binary patterns. Biomed Signal Process Control 2015;15:33–40.
• [45] Zhang Y, Zhou W, Yuan S. Multifractal analysis and relevance vector machine-based automatic seizure detection in intracranial eeg. Int J Neural Syst 2015;25 (6):1550020.
• [46] Wang L, Xue W, Li Y, Luo M, Huang J, Cui W, et al. Automatic epileptic seizure detection in eeg signals using multi-domain feature extraction and nonlinear analysis. Entropy 2017;19(222).
• [47] Bhattacharyya A, Pachori RB. A multivariate approach for patient specific eeg seizure detection using empirical wavelet transform. IEEE Trans Biomed Eng 2017;64(9):2003–15.
• [48] Bhati D, Sharma M, Pachori RB, Gadre VM. Time-frequency localized three- band biorthogonal wavelet filter bank using semidefinite relaxation and nonlinear least squares with epileptic seizure eeg signal classification. Digit Signal Process 2017;62:259–73.
• [49] Tiwari AK, Pachori RB, Kanhangad V, Panigrahi BK. Automated diagnosis of epilepsy using key-points based local binary pattern of eeg signals. IEEE J Biomed Health Inf 2017;21(4):888–96.
• [50] Sharma RR, Pachori RB. Time-frequency representation using ievdhm-ht with application to classification of epileptic eeg signals, IET Science. Meas Technol 2018;12(01):72–82.
• [51] Mallat S. A Wavelet Tour of Signal Processing. Academic Press; 2008.
• [52] Do MN, Vetterli M. Wavelet-based texture retrieval using generalized Gaussian density and Kullback–Leibler distance. IEEE Trans Image Process 2002;11(2):146–58.
• [53] Pascal F, Bombrun L, Tourneret J-Y, Berthoumieu Y. Parameter estimation for multivariate generalized gaussian distributions. IEEE Trans Signal Process 2013;61(23):5960–71.
• [54] Goldberger A, Amaral L, Glass L, Hausdorff J, Ivanov P, Mark R, et al. Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 2000;101(23):e215–20.
• [55] Bandarabadi M, Rasekhi J, Teixeira CA, Netoff TI, Parhi KK, Dourado A. Early seizure detection using neuronal potential similarity: a generalized low-complexity and robust measure. Int J Neural Syst 2015;25(05):1550019.
• [56] Quintero-Rincón A, Pereyra M, D'Giano C, Batatia H, Risk M. A new algorithm for epilepsy seizure onset detection and spread estimation from eeg signals. J Phys: Conf Ser 2016;705(1):012032.
• [57] Quintero-Rincón A, Prendes J, Pereyra M, Batatia H, Risk M. Multivariate Bayesian classification of epilepsy eeg signals. IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). 2016. pp. 1–5.
• [58] Quintero-Rincón A, Pereyra M, D'giano C, Batatia H, Risk M. A visual eeg epilepsy detection method based on a wavelet statistical representation and the Kullback–Leibler divergence. Int Feder Med Biol Eng (IFMBE) Proc 2017; 60:13–6.
• [59] Laha RC. Handbook of methods of Applied Statistics Volume I: Techniques of computation, descriptive methods and statistical inference. John Wiley and Sons; 1967.
• [60] Anderson T. On the distribution of the two-sample Cramervon Mises criterion. Ann Math Stat 1962;33(3):1148–59.
• [61] Johnson VE. Uniformly most powerful Bayesian test. Ann Stat 2013;41:1716–41.