A multistage, multimethod approach for automatic detection and classification of epileptiform EEG

An efficient system for detection of epileptic activity in ambulatory electroencephalogram (EEG) must be sensitive to abnormalities while keeping the false-detection rate to a low level. Such requirements could be fulfilled neither by a single stage nor by a simple method strategy, due to the extreme variety of EEG morphologies and frequency of artifacts. The present study proposes a robust system that combines multiple signal-processing methods in a multistage scheme, integrating adaptive filtering, wavelet transform, an artificial neural network, and expert system. The system consists of two main stages: a preliminary screening stage in which data are reduced significantly, followed by an analytical stage. Unlike most systems that merely focus on sharp transients, our system also takes into account slow waves. A nonlinear filter for separation of nonstationary and stationary EEG components is also developed. The system was evaluated on testing data from 81 patients, totaling more than 800 hours of recordings. 90.0% of the epileptic events were correctly detected. The detection rate of sharp transients was 98.0% and overall false-detection rate was 6.1%. We conclude that our system has good performance in detecting epileptiform activities and the multistage multimethod approach is an appropriate way of solving this problem.

[1]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[2]  I. Yaylali,et al.  Detection of seizures from small samples using nonlinear dynamic system theory , 1996, IEEE Transactions on Biomedical Engineering.

[3]  E. Waterhouse,et al.  New horizons in ambulatory electroencephalography , 2003, IEEE Engineering in Medicine and Biology Magazine.

[4]  A. Geva,et al.  Forecasting generalized epileptic seizures from the EEG signal by wavelet analysis and dynamic unsupervised fuzzy clustering , 1998, IEEE Transactions on Biomedical Engineering.

[5]  J. R. Glover,et al.  Continued Development Of A Knowledge-based System To Detect Epileptogenic Sharp Transients In The EEG , 1990, [1990] Proceedings of the Twelfth Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  D. Lehmann,et al.  Handbook of electroencephalography and clinical neurophysiology , 1976 .

[7]  W.R. Fright,et al.  A multistage system to detect epileptiform activity in the EEG , 1993, IEEE Transactions on Biomedical Engineering.

[8]  I. Bankman,et al.  Automatic EEG spike detection: what should the computer imitate? , 1993, Electroencephalography and clinical neurophysiology.

[9]  J. Gotman,et al.  Automatic seizure detection in the newborn: methods and initial evaluation. , 1997, Electroencephalography and clinical neurophysiology.

[10]  Lamberto Cesari,et al.  Optimization-Theory And Applications , 1983 .

[11]  P. Bertrand,et al.  Discrete Mellin transform for signal analysis , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[12]  W R Webber,et al.  An approach to seizure detection using an artificial neural network (ANN). , 1996, Electroencephalography and clinical neurophysiology.

[13]  Ramesh A. Gopinath,et al.  Efficient computation of the wavelet transforms , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[14]  W. van Emde Boas,et al.  Sharp transients in the sleep EEG of healthy adults: a possible pitfall in the diagnostic assessment of seizure disorders. , 1998, Electroencephalography and clinical neurophysiology.

[15]  Hsiao-Wen Chung,et al.  Automatic spike detection via an artificial neural network using raw EEG data: effects of data preparation and implications in the limitations of online recognition , 2000, Clinical Neurophysiology.

[16]  M Unser,et al.  Fast wavelet transformation of EEG. , 1994, Electroencephalography and clinical neurophysiology.

[17]  Hiroshi Harashima,et al.  A nonlinear digital filter for separating nonstationary waves from stationary waves of the EEG , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Sankar K. Pal,et al.  Multilayer perceptron, fuzzy sets, and classification , 1992, IEEE Trans. Neural Networks.

[19]  Luis Diambra,et al.  Epileptic activity recognition in EEG recording , 1999 .

[20]  John R. Glover,et al.  A Multichannel Signal Processor for the Detection of Epileptogenic Sharp Transients in the EEG , 1986, IEEE Transactions on Biomedical Engineering.

[21]  Flavio Sartoretto,et al.  Automatic detection of epileptiform activity by single-level wavelet analysis , 1999, Clinical Neurophysiology.

[22]  Ronald G. Emerson,et al.  Spike detection II: automatic, perception-based detection and clustering , 1999, Clinical Neurophysiology.

[23]  J. Gotman,et al.  Improvement in seizure detection performance by automatic adaptation to the EEG of each patient. , 1993, Electroencephalography and clinical neurophysiology.

[24]  Antoine Rémond,et al.  Methods of Analysis of Brain Electrical and Magnetic Signals , 1987 .

[25]  R. Eberhart.  Chaos theory for the biomedical engineer , 1989, IEEE Engineering in Medicine and Biology Magazine.

[26]  J. S. Barlow,et al.  EEG transient detection by matched inverse digital filtering. , 1980, Electroencephalography and clinical neurophysiology.

[27]  O. Ozdamar,et al.  Wavelet preprocessing for automated neural network detection of EEG spikes , 1995 .

[28]  A J Gabor,et al.  Automated seizure detection using a self-organizing neural network. , 1996, Electroencephalography and clinical neurophysiology.

[29]  J. Gotman,et al.  Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG. , 1976, Electroencephalography and Clinical Neurophysiology.

[30]  R Sankar,et al.  Automatic computer analysis of transients in EEG. , 1992, Computers in biology and medicine.

[31]  Richard D. Jones,et al.  The Use Of Multi-channel Information In The Detection Of Epileptiform Activity In The EEG , 1990, [1990] Proceedings of the Twelfth Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  Yuan-Ting Zhang,et al.  Localization of hearing loss on the basis of transient-evoked otoacoustic emissions by using wavelet transform , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[33]  Tong Zhang,et al.  Content-Based Audio Classification and Retrieval for Audiovisual Data Parsing , 2001 .

[34]  Khashayar Khorasani,et al.  An Adaptive Structure Neural Networks with Application to EEG Automatic Seizure Detection , 1996, Neural Networks.

[35]  Yang Fusheng,et al.  A fast algorithm of continuous wavelet transform based on Mellin transform with biomedical application , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[36]  J. Frost,et al.  Context-based automated detection of epileptogenic sharp transients in the EEG: elimination of false positives , 1989, IEEE Transactions on Biomedical Engineering.

[37]  Douglas L. Jones,et al.  Efficient approximation of continuous wavelet transforms , 1991 .

[38]  W E Hostetler,et al.  Assessment of a computer program to detect epileptiform spikes. , 1992, Electroencephalography and clinical neurophysiology.