Epileptic seizure detection based on improved wavelet neural networks in long-term intracranial EEG

• Autorzy: Geng D. , Zhou W. , Zhang Y. , Geng S.

Identyfikatory

DOI

10.1016/j.bbe.2016.03.001

• Języki publikacji: EN

Abstrakty

EN

Automatic seizure detection is of great importance for speeding up the inspection process and relieving the workload of medical staff in the analysis of EEG recordings. In this study, a method based on an improved wavelet neural network (WNN) is proposed for automatic seizure detection in long-term intracranial EEG. WNN combines the traditional back propagation neural network (BPNN) with wavelet transform. Compared with classic WNN architectures, a modified point symmetry-based fuzzy c-means (MSFCM) algorithm is applied to the initialization of wavelet transform's translations, which has been successful in multiclass cancer classification. In addition, Fast-decaying Morlet wavelet is chosen as the activation function to make the WNN learn faster. Relative amplitude and relative fluctuation index are extracted as a feature vector to describe the variation of EEG signals, and the feature vector is then fed into WNN for classification. At last, post-processing including smoothing, channel fusion and collar technique is adopted to achieve more accurate and stable results. This system performs efficiently with the average sensitivity of 96.72%, specificity of 98.91% and false-detection rate of 0.27 h^_1. The proposed approach achieves high sensitivity and low false detection rate, which demonstrates its potential for clinical usage.

Słowa kluczowe

EN

seizure detection; EEG signal; modified point symmetry-based fuzzy c-means; wavelet neural network

PL

wykrywanie napadu; sygnał EEG; sieć falkowo-neuronowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2016
• Tom: Vol. 36, no. 2
• Strony: 375--384
• Opis fizyczny: Bibliogr. 31 poz., rys., tab., wykr.

Twórcy

autor

Geng D.

• School of Information Science and Engineering, Shandong University, Jinan, PR China; Suzhou Institute of Shandong University, Suzhou, PR China

autor

Zhou W.

• School of Information Science and Engineering, Shandong University, 27 Shanda Road, Jinan 250100, PR China; Suzhou Institute of Shandong University, Suzhou, PR China

autor

Zhang Y.

• School of Information Science and Engineering, Shandong University, Jinan, PR China; Suzhou Institute of Shandong University, Suzhou, PR China

autor

Geng S.

• School of Information Science and Engineering, Shandong University, Jinan, PR China; Suzhou Institute of Shandong University, Suzhou, PR China

Bibliografia

• [1] Niedermeyer E, Lopes da Silva F. Electroencephalography: basic principles, clinical applications, and related fields. 5th ed. Philadelphia: Lippincott Williams &Wilkins; 2005.
• [2] Netoff TI, Schiff SJ. Decreased neuronal synchronization during experimental seizures. J Neurosci 2002;22(16): 7297–307.
• [3] Sanei S, Chambers JA. EEG signal processing. Chichester: John Wiley & Sons Ltd; 2007.
• [4] Misra UK, Kalita J. Clinical electroencephalography. 1st ed. Noida: Elsevier, a division of Reed Elsevier India Private Limited; 2005.
• [5] Lehnertz K, Mormann F, Kreuz T, Andrzeiak RG, Rieke C, David P, et al. Seizure prediction by nonlinear EEG analysis. IEEE Eng Med Biol Mag 2003;22(1):57–63.
• [6] Gandhi T, Panigrahi BK, Bhatia M, Anand S. Expert model for detection of epileptic activity in EEG signature. Expert Syst Appl 2010;37(4):3513–20.
• [7] Gotman J. Automatic recognition of epileptic seizures in the EEG. Electroencephalogr Clin Neurophysiol 1982;54 (5):530–40.
• [8] Hao Q, Gotman J. Improvement in seizure detection performance by automatic adaptation to the EEG of each patient. Electroencephalogr Clin Neurophysiol 1993;86 (2):79–87.
• [9] Gotman J. Automatic seizure detection: improvements and evaluation. Electroencephalogr Clin Neurophysiol 1990;76 (4):317–24.
• [10] Osorio I, Frei MG, Wilkinson SB. Real-time automated detection and quantitative analysis of seizures and short-term prediction of clinical onset. Epilepsia 1998;39 (6):615–27.
• [11] Khan YU, Gotman J. Wavelet based automatic seizure detection in intracerebral electroencephalogram. Clin Neurophysiol 2003;114(5):898–908.
• [12] Geng SJ, Zhou WD, Yao QM, Ma Z. Nonlinear analysis of EEG using fractal dimension and approximate entropy. Adv Mater Res 2012;532-533:988–92.
• [13] Yuan Q, Zhou W, Li S, Cai D. Epileptic EEG classification based on extreme learning machine and nonlinear features. Epilepsy Res 2011;1(1-2):29–38.
• [14] Wang Y, Zhou W, Yuan Q, Li X, Meng Q, Zhao X, et al. Comparison of ictal and interictal EEG signals using fractal features. Int J Neural Syst 2013;23(6):793–804.
• [15] Alexandridis AK, Zapranis AD. Wavelet neural networks: with applications in financial engineering, chaos and classification. Wiley; 2014.
• [16] Zainuddin Z, Ong P. Reliable multiclass cancer classification of microarray gene expression profiles using an improved wavelet neural network. Expert Syst Appl 2011;38 (11):13711–22.
• [17] Zainuddin Z, Ong P. Design of wavelet neural networks based on symmetry fuzzy C-means for function approximation. Neural Comp Appl 2013;23(1 Suppl.):247–59.
• [18] Freiburg seizure prediction project. Freburg, Germany. 2008. Available: http://epilepsy.uni-freburg.de/ freiburg-seizure-prediction-project/eeg-database.
• [19] Grewal S, Gotman J. An automatic warning system for epileptic seizures recorded on intracerebral EEGs. Clin Neurophysiol Off J Int Fed Clin Neurophysiol 2005;116 (10):2460–72.
• [20] Qi Y, Zhou W, Liu Y, Wang J. Epileptic seizure detection with linear and nonlinear features. Epilepsy Behav 2012;24 (4):415–21.
• [21] Liang J, Elangovan S, Devotta JBX. Application of wavelet transform in travelling wave protection. Elect Power Energy Syst 2000;22(8):537–42.
• [22] Strang G, Nguyen T. Wavelets and filter banks. Wellesley- Cambridge Press; 1996.
• [23] Pindoriya NM, Singh SN, Singh SK. An adaptive wavelet neural network-based energy price forecasting in electricity markets. Power Syst IEEE Trans 2008;23(3):1423–32.
• [24] Tezel G, Özbay Y. A new approach for epileptic seizure detection using adaptive neural network. Expert Syst Appl 2009;36(1):172–80.
• [25] Bajaj V, Pachori RB. Epileptic seizure detection based on the instantaneous area of analytic intrinsic mode functions of EEG signals. Biomed Eng Lett 2013;03(1):17–21.
• [26] Liu Y, Zhou W, Yuan Q, Chen S. Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG. IEEE Trans Neural Syst Rehab Eng Pub IEEE Eng Med Biol Soc 2012;20(6):749–55.
• [27] Chua CP, Patel K, Fitzsimons M, Bleakley CJ. Improved patient specific seizure detection during pre-surgical evaluation. Clin Neurophysiol Off J Int Fed Clin Neurophysiol 2011;122(4):672–9.
• [28] Irazoqui PP, Raghunathan S, Jaitli A. Multistage seizure detection techniques optimized for low-power hardware platforms. Epilepsy Behav 2011;22(4):S61–8.
• [29] Majumdar KK, Vardhan P. Automatic seizure detection in ECoG by differential operator and windowed variance. IEEE Trans Neural Syst Rehab Eng Pub IEEE Eng Med Biol Soc 2011;19(4):356–65.
• [30] Yuan S, Zhou W, Qi Y, Zhang Y, Meng Q. Automatic seizure detection using diffusion distance and BLDA in intracranial EEG. Epilepsy Behav 2014;31(2):339–45.
• [31] Rabbi AF, Fazel-Rezai R. A fuzzy logic system for seizure onset detection in intracranial EEG. Computat Intell Neurosci 2012;2012(1):167–85.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.