A Method for Classification of Transient Events in EEG Recordings: Application to Epilepsy Diagnosis

Summary

Objectives: The aim of the paper is to analyze transient events in inter-ictal EEG recordings, and classify epileptic activity into focal or generalized epilepsy using an automated method.

Methods: A two-stage approach is proposed. In the first stage the observed transient events of a single channel are classified into four categories: epileptic spike (ES), muscle activity (EMG), eye blinking activity (EOG), and sharp alpha activity (SAA). The process is based on an artificial neural network. Different artificial neural network architectures have been tried and the network having the lowest error has been selected using the hold out approach. In the second stage a knowledge-based system is used to produce diagnosis for focal or generalized epileptic activity.

Results: The classification of transient events reported high overall accuracy (84.48%), while the knowledge-based system for epilepsy diagnosis correctly classified nine out of ten cases.

Conclusions: The proposed method is advantageous since it effectively detects and classifies the undesirable activity into appropriate categories and produces a final outcome related to the existence of epilepsy.

Keywords

EEG - automated epilepsy diagnosis - clustering - artificial neural networks - spike detection - knowledge-based system

• References

• 1 Niedermeyer E, Silva F. Electroencephalography, Basic Principles, Clinical Applications, and Related Fields. Baltimore: Williams and Wilkins; 1993
• 2 Sundaram M, Sadler RM, Young GB, Pillay N. EEG in Epilepsy: Current Perspectives. Can J Neurol Sci 1999; 26: 255-62.
• 3 Haines S. EEG Questions and Answers. [Online] Available www.neuro.wustl.edu./epilepsy/pediatric/articleEEG.html date accessed 29/11/2004.
• 4 Gloor P. Contribution of electroencephalography and electrocorticography in the neurosurgical treatment of the epilepsies. Adv Neurol 1975; 8
• 5 McGrogan N. Neural Network Detection of Epileptic Seizures in the Electroencephalogram. Ph.D. Thesis. Oxford University; February1999.
• 6 Frost JD. Automatic recognition and characterization of epileptiform discharges in the human EEG. J Clin Neurophysiol 1985; 2: 231-49.
• 7 Gotman J, Gloor P. Automatic recognition of inter-ictal epileptic activity in the human scalp EEG recordings. Electroenceph Clin Neurophysiol 1976; 41: 513-29.
• 8 Tarassenko L, Khan YU, Holt MRG. Identification of inter-ictal spikes in the EEG using neural network analysis. In: Proc IEE Sci Meas Technol 1998; 145: 270-8.
• 9 Wilson SB, Emerson R. Spike Detection: a review and comparison of algorithms. Clin Neurophysiol 2002; 113: 1873-81.
• 10 Gotman J. Automatic recognition of epileptic seizures in the EEG. Electroenceph Clin Neurophysiol 1982; 54: 530-40.
• 11 Guedes de Oliveira P, Queiroz C, Lopes de Silva F. Spike detection based on a pattern recognition approach using a microcomputer. Electroenceph Clin Neurophysiol 1983; 56: 97-103.
• 12 Ktonas P, Luoh W, Kejariwal M, Seward M. Computer- aided quantification of EEG spike and sharp characteristics. Electroenceph Clin Neurophysiol 1981; 51: 237-43.
• 13 Ktonas P, Glover J, Webster L, Antonthanasap R, Van Leeuwen W, Van Veelen C, Vliegenthart W. Automatic detection of epileptogenic sharp EEG transients. Electroenceph Clin Neurophysiol 1984; 38-58.
• 14 Kalayci T, Ozdamar O. Wavelet pre-processing for automated neural network detection of EEG spikes. IEEE Eng Med Biology 1995; 14: 160-6.
• 15 Lopes FH. da Silva. Detection of nonstationarities in EEGs using the autoregressive model - an application to EEGs of epileptics. In Dolce G, Kunkel H. (eds.) CEAN: computerized EEG analysis. Stuttgart 1975; pp 180-99.
• 16 Diambra L, Malta C. Nonlinear models for epileptic spikes. Physical Review E 1999; 59: 929-37.
• 17 Gabor AJ, Seyal M. Automated interictal EEG spike detection using artificial neural networks. Electroenceph Clin Neurophysiol 1992; 83: 271-80.
• 18 Gabor AJ, Leach RR, Dowla FU. Automated seizure detection using a self-organizing neural network. Electroenceph Clin Neurophysiol 1996; 99: 257-66.
• 19 Gabor AJ. Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies. Electroenceph Clin Neurophysiol 1998; 107: 27-32.
• 20 Webber WR, Litt B, Wilson K, Lesser RP. Practical detection of epileptiform discharges (EDs) in the EEG using an artificial neural network: a comparison of raw and parameterized EEG data. Electroenceph Clin Neurophysiol 1994; 91: 194-204.
• 21 Webber W, Lesser RP, Richardson R, Wilson K. An approach to seizure detection using an artificial neural network (ANN). Electroenceph Clin Neurophysiol 1996; 98: 250-72.
• 22 Park HS, Lee YH, Kim NG, Lee DS, Kim SI. Detection of epileptiform activities in the EEG using neural network and expert system. Medinfo 1998; 9: 1255-9.
• 23 Ozdamar O, Kalayci T. Detection of spikes with artificial neural networks using raw EEG. Comput Biomed. Res 1998; 31: 122-42.
• 24 James JC, Jones RD, Bones PJ, Carroll GJ. Detection of epileptiform discharges in the EEG by a hybrid system compromising mimetic, self-organized artificial neural network, and fuzzy logic stages. Clin Neurophysiol 1999; 110: 2049-63.
• 25 Hellmann G. Multifold features determine linear equation for automatic spike detection applying neural network interictal ECoG. Clin Neurophysiol 1999; 110: 887-94.
• 26 Ko CW, Chung HW. Automatic spike detection via artificial neural network using raw EEG data: effects of data preparation and implications in the limitations of online recognition. Clin Neurophysiol 2000; 111: 477-81.
• 27 Petrosian A, Prokhorov D, Homan R, Dasheif R, Wunch D. Recurrent neural network-based prediction of epileptic seizure in intra- and extra-cranial EEG. Neurocomputing 2000; 30: 201-18.
• 28 Pang CCC, Upton ARM, Shine G, Kamath MV. A Comparison of Algorithms for Detection of Spikes in the Electroencephalogram. IEEE Transactions on Biomedical Engineering 2003; 50: 521-5.
• 29 Acir N, Oztura I, Kuntalp M, Balkan B, Guzelis C. Automatic detection of Epileptiform Events in EEG by a Three Stage Procedure Based on Artificial Neural Networks. IEEE Trans on Biomed Eng 2005; 52: 30-40.
• 30 Schiff S, Aldroubi A, Unser M, Sato S. Fast wavelet transformation of EEG. Electroenceph Clin Neurophysiol 1994; 91: 442-55.
• 31 Senhadji L, Dillenseger JL, Wendling F, Rocha C, Kinie A. Wavelet analysis of EEG for 3-dimensional mapping of epileptic events. Ann Biomed Eng 1995; 23: 543-52.
• 32 Senhadji L, Wendling F. Epileptic transient detection: wavelets and time-frequency approaches. Neurophysiol Clin 2002; 32: 175-92.
• 33 Goelz H, Jones RD, Bones PJ. Wavelet analysis of transient biomedical signals and its application to detection of epileptiform activity in the EEG. Clin Electroenceph 2000; 31: 181-91.
• 34 Castellaro C, Favaro G, Castellaro A, Casagrande A, Castellaro S, Puthenparampil DV, Salimbeni CF. An artificial intelligence approach to classify and analyse EEG traces. Neurophysiol Clin 2002; 32: 193-214.
• 35 Agarwal R, Gotman J, Flanagan D, Rosenblatt B. Automatic EEG analysis during long-term monitoring in the ICU. Electroenceph Clin Neurophysiol 1998; 107: 44-58.
• 36 Davey BL, Fright WR, Carroll GJ, Jones RD. Expert system approach to detection of epileptiform activity in the EEG. Med Biol Eng Comput 1989; 27: 365-70.
• 37 Dingle AA, Jones RD, Carroll GJ, Fright WR. A multistage system to detect epileptiform activity in the EEG. IEEE Trans Biomed Eng 1993; 40: 1260-8.
• 38 Benlamri R, Batouche M, Rami S, Bounaka C. An automated system for analysis and interpretation of epileptiform activity in the EEG. Comput Biol Med 1997; 27: 129-39.
• 39 Barlow JS, Creutzfeldt OD, Michael D, Houchin J, Epelbaum H. Automatic adaptive segmentation of EEGs. Electroenceph Clin Neurophysiol 1981; 51: 512-25.
• 40 Wahlberg P, Lantz G. Methods for robust clustering of epileptic EEG spikes. IEEE Trans Biomed Eng 2000; 47: 857-68.
• 41 Katsis CD, Goletsis Y, Likas A, Fotiadis DI, Sarmas I. A novel method for automated EMG decomposition and MUAP classification. Artif Intel in Med 2006; 37: 55-64.
• 42 Acir N, Guzelis C. Automatic spike detection in EEG by a two stage procedure based on support vector machine. Comp in Biol and Med 2004; 34: 561-75.
• 43 Kothari R, Pitts D. On finding the number of clusters. Patt Rec Letters 1999; 20: 405-16.
• 44 Kong X, Qiu T. Injury Detection for Central Nervous System via EEG with High Order Crossingbased Methods. Methods Inf Med 2000; 39: 171-4.
• 45 Bishop CM. Neural Networks for Pattern Recognition. Oxford: University Press 1995
• 46 Jasper HH. The Ten Twenty Electrode System of the International Federation. Clinical Neurophysiology 1958; 10: 371-5.
• 47 Cincotti F, Mattia D, Babiloni C, Carducci F, Bianchi L, Del R, Millán J, Mouriño J, Salinari S, Marciani MG, Babiloni F. Classification of EEG Mental Patterns by Using Two Scalp Electrodes and Mahalanobis Distance-Based Classifiers. Methods Inf Med 2002; 41: 337-41.
• 48 Tzallas AT, Katsis CD, Karvelis PS, Fotiadis DI, Konitsiotis S, Giannopoulos S. Classification of Transient Events in EEG Recordings. In: Proceedings of the IEE Medical Signal and Information Processing Conference (MEDSIP), Malta, September 5-8 2004; pp 14-20.
• 49 Exarchos TP, Tzallas AT, Fotiadis DI, Konitsiotis S, Giannopoulos S. A Data Mining Based Approach for the EEG Transient Event Detection and Classification. In: Proceedings of the 18th IEEE Symposium on Computer-Based Medical Systems (CBMS’05), Ireland, June 23-24 2005; pp 35-40.
• 50 Panayiotopoulos CP. Early-onset benign childhood occipital seizure susceptibility syndrome: a syndrome to recognize. Epilepsia 1999; 40: 621-30.