A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram

We describe a strategy to automatically identify epileptiform activity in 18-channel human electroencephalogram (EEG) based on a multi-resolution, multi-level analysis. The signal on each channel is decomposed into six sub-bands using discrete wavelet transform. Adaptive threshold is applied on sub-bands 4 and 5. The spike portion of EEG signal is then extracted from the raw data and energy of the signal for locating the exact location of epileptic foci is determined. The key points of this process are identification of a suitable wavelet for decomposition of EEG signals, recognition of a proper resolution level, and computation of an appropriate dynamic threshold.

[1]  Zhi-Qiang Liu,et al.  Electroencephalogram analysis using fast wavelet transform , 2001, Comput. Biol. Medicine.

[2]  K. Radhakrishnan,et al.  Prevalence of benign epileptiform variants observed in an EEG laboratory from South India , 1999, Clinical Neurophysiology.

[3]  Rodica Strungaru,et al.  Independent Component Analysis Applied in Biomedical Signal Processing , 2004 .

[4]  H. Berger,et al.  Über das Elektrenkephalogramm des Menschen , 1937, Archiv für Psychiatrie und Nervenkrankheiten.

[5]  G. Deuschl,et al.  Recommendations for the practice of clinical neurophysiology: guidelines of the International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[6]  Richard Wennberg.  Modern electroencephalography: its role in epilepsy management , 2000, Clinical Neurophysiology.

[7]  Carlos E. D'Attellis,et al.  Detection of epileptic events in electroencephalograms using wavelet analysis , 2007, Annals of Biomedical Engineering.

[8]  Bruce J. West,et al.  Wavelet analysis of epileptic spikes. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Giancarlo Calvagno,et al.  A multiresolution approach to spike detection in EEG , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[10]  R Biscay,et al.  Multiresolution decomposition of non-stationary EEG signals: a preliminary study. , 1995, Computers in biology and medicine.

[11]  Piotr J Durka.  Adaptive time-frequency parametrization of epileptic spikes. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  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.

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

[14]  Joseph R. Cavallaro,et al.  VLSI implementation of Mallat's fast discrete wavelet transform algorithm with reduced complexity , 2001, GLOBECOM'01. IEEE Global Telecommunications Conference (Cat. No.01CH37270).

[15]  Tong Zhang,et al.  A multistage, multimethod approach for automatic detection and classification of epileptiform EEG , 2002, IEEE Transactions on Biomedical Engineering.

[16]  Michael Unser,et al.  A review of wavelets in biomedical applications , 1996, Proc. IEEE.

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

[18]  M. Farrokhi,et al.  EEG features extraction using neuro-fuzzy systems and shift-invariant wavelet transforms for epileptic seizures diagnosing , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  C.J. James,et al.  Tracking Epileptiform Activity in the Multichannel Ictal EEG using Spatially Constrained Independent Component Analysis , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[20]  Wilson C. K. Poon,et al.  Phase behavior and crystallization kinetics of PHSA-coated PMMA colloids , 2003 .

[21]  C. Binnie,et al.  A glossary of terms most commonly used by clinical electroencephalographers. , 1974, Electroencephalography and clinical neurophysiology.

[22]  S. Mukhopadhyay,et al.  A new interpretation of nonlinear energy operator and its efficacy in spike detection , 1998, IEEE Transactions on Biomedical Engineering.

[23]  Nurettin Acir,et al.  Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks , 2005, IEEE Transactions on Biomedical Engineering.

[24]  C. Binnie,et al.  Glossar der meistgebrauchten Begriffe in der klinischen Elektroenzephalographie und Vorschläge für die EEG-Befunderstellung , 2004 .

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

[26]  J. Wolpaw,et al.  EMG contamination of EEG: spectral and topographical characteristics , 2003, Clinical Neurophysiology.

[27]  B. Westmoreland,et al.  Nonepileptogenic epileptiform electroencephalographic activity , 1985, Annals of neurology.

[28]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  P. Kellaway,et al.  Proposal for Revised Clinical and Electroencephalographic Classification of Epileptic Seizures , 1981, Epilepsia.

[30]  Mostefa Mesbah,et al.  EEG spike detection using time-frequency signal analysis , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[31]  Abdulhamit Subasi.  Automatic detection of epileptic seizure using dynamic fuzzy neural networks , 2006, Expert Syst. Appl..

[32]  B. Westmoreland,et al.  Epileptiform electroencephalographic patterns. , 1996, Mayo Clinic proceedings.