Detection of spikes with artificial neural networks using raw EEG.

Artificial neural networks (ANN) using raw electroencephalogram (EEG) data were developed and tested off-line to detect transient epileptiform discharges (spike and spike/wave) and EMG activity in an ongoing EEG. In the present study, a feedforward ANN with a variable number of input and hidden layer units and two output units was used to optimize the detection system. The ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. The effects of different EEG time windows and the number of hidden layer neurons were examined using rigorous statistical tests for optimum detection sensitivity and selectivity. The best ANN configuration occurred with an input time window of 150 msec (30 input units) and six hidden layer neurons. This input interval contained information on the wave component of the epileptiform discharge which improved detection. Two-dimensional receiver operating curves were developed to define the optimum threshold parameters for best detection. Comparison with previous networks using raw EEG showed improvement in both sensitivity and selectivity. This study showed that raw EEG can be successfully used to train ANNs to detect epileptogenic discharges with a high success rate without resorting to experimenter-selected parameters which may limit the efficiency of the system.

[1]  Russell C. Eberhart,et al.  CaseNet: a neural network tool for EEG waveform classification , 1989, [1989] Proceedings. Second Annual IEEE Symposium on Computer-based Medical Systems.

[2]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[3]  W R Webber,et al.  Practical detection of epileptiform discharges (EDs) in the EEG using an artificial neural network: a comparison of raw and parameterized EEG data. , 1994, Electroencephalography and clinical neurophysiology.

[4]  A J Gabor,et al.  Automated interictal EEG spike detection using artificial neural networks. , 1992, Electroencephalography and clinical neurophysiology.

[5]  Ozcan Ozdaa,et al.  Real-time detection of EEG spikes using neural networks , 1992, 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  J D Frost,et al.  Automatic Recognition and Characterization of Epileptiform Discharges in the Human EEG , 1985, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[7]  Russell C. Eberhart,et al.  Case study I: the detection of electroencephalogram spikes , 1990 .

[8]  Özcan Özdamar,et al.  Auditory brainstem evoked potential classification for threshold detection by neural networks. I. Network design, similarities between human-expert and network classification, feasibility , 1992 .

[9]  J R Ives,et al.  Automatic recognition of inter-ictal epileptic activity in prolonged EEG recordings. , 1979, Electroencephalography and clinical neurophysiology.

[10]  G. Pfurtscheller,et al.  A new approach to spike detection using a combination of inverse and matched filter techniques. , 1978, Electroencephalography and clinical neurophysiology.

[11]  J Gotman,et al.  Comparison of traditional reading of the EEG and automatic recognition of interictal epileptic activity. , 1978, Electroencephalography and clinical neurophysiology.

[12]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[13]  R. H. Myers,et al.  Probability and Statistics for Engineers and Scientists , 1978 .

[14]  O. Ozdamar,et al.  Detection of transient EEG patterns with adaptive unsupervised neural networks , 1992, Proceedings of the 1992 International Biomedical Engineering Days.

[15]  Ilker Yaylali,et al.  Multilevel neural network system for EEG spike detection , 1991, [1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium.

[16]  P Gloor,et al.  Long-term monitoring in epilepsy. , 1985, Electroencephalography and clinical neurophysiology. Supplement.

[17]  J. R. Smith,et al.  Automatic recognition of spike and wave bursts. , 1985, Electroencephalography and clinical neurophysiology. Supplement.

[18]  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.

[19]  M D Craggs,et al.  The validation of a new ambulatory spike and wave monitor. , 1989, Electroencephalography and clinical neurophysiology.

[20]  K. Horch,et al.  Classification of action potentials in multi-unit intrafascicular recordings using neural network pattern-recognition techniques , 1994 .

[21]  Qiuzhen Xue,et al.  Late potential recognition by artificial neural networks , 1997, IEEE Transactions on Biomedical Engineering.

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

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

[24]  Kaoru Arakawa,et al.  Separation of a Nonstationary Component from the EEG by a Nonlinear Digital Filter , 1986, IEEE Transactions on Biomedical Engineering.

[25]  W T Blume,et al.  Morphology of spikes in spike-and-wave complexes. , 1988, Electroencephalography and clinical neurophysiology.

[26]  B. G. Batchelor,et al.  Pattern Recognition in EEG , 1972 .

[27]  P Guedes de Oliveira,et al.  Spike detection based on a pattern recognition approach using a microcomputer. , 1983, Electroencephalography and clinical neurophysiology.

[28]  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.

[29]  Edward R. Dougherty,et al.  Probability and Statistics for the Engineering, Computing and Physical Sciences , 1990 .

[30]  J. Gotman,et al.  State dependent spike detection: validation. , 1992, Electroencephalography and clinical neurophysiology.

[31]  Ah Chung Tsoi,et al.  Efficacy of modified backpropagation and optimisation methods on a real-world medical problem , 1995, Neural Networks.

[32]  J Gotman,et al.  State-dependent spike detection: concepts and preliminary results. , 1991, Electroencephalography and clinical neurophysiology.

[33]  Lars H. Zetterberg,et al.  CEAN-computerized EEG analysis , 1977 .

[34]  Özcan Özdamar,et al.  Auditory brainstem evoked potential classification for threshold detection by neural networks. II. Effects of input coding, training set size and composition and network size on performance , 1992 .

[35]  B. L. Kalman,et al.  Why tanh: choosing a sigmoidal function , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

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