Automatic Seizure Detection in ECoG by Differential Operator and Windowed Variance

Differential operator has long been used in image and signal processing with great success to detect significant changes. In this paper we show that differentiation can enhance certain features of brain electrophysiological signals, contaminated with noise, artifacts, and acquisition defects, leading to efficient detection of those changes. Windowed variance method has been very successful in detecting seizure onset in the brain electrophysiological signals. In this paper we have combined these two powerful methods under the name of differential windowed variance (DWV) algorithm to automatically detect seizure onsets in almost real time, in continuous ECoG (depth-EEG) signals of epileptic patients. The main advantages of the method are simplicity of implementation and speed. We have tested the algorithm on 369 h of nonseizure ECoG as well as 59 h of seizure ECoG of 15 epileptic patients. It detected all but six seizures (91.525% accuracy) with an average delay of 9.2 s after the onset with a maximum false detection of three in 24 h of nonseizure data. Eight novel empirical measures have been introduced to avoid false detections. To ascertain the reliability of the detection method a novel methodology, called quasi-ROC (qROC) curve analysis has been introduced. DWV has been compared with a difference filter based sharp transient (ST) detection algorithm.

[1]  Walter Krämer.  Wojtek J. Krzanowski and David J. Hand: ROC curves for continuous data , 2011 .

[2]  Asla Pitkänen,et al.  Epileptic seizure detection: A nonlinear viewpoint , 2005, Comput. Methods Programs Biomed..

[3]  A. Schulze-Bonhage,et al.  How well can epileptic seizures be predicted? An evaluation of a nonlinear method. , 2003, Brain : a journal of neurology.

[4]  Hyong C Lee,et al.  Comparison of Seizure Detection Algorithms in Continuously Monitored Pediatric Patients , 2007, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[5]  J. S. Barlow,et al.  A simplified arithmetic detector for EEG sharp transients-preliminary results , 1988, IEEE Transactions on Biomedical Engineering.

[6]  Lenka Lhotská,et al.  Neonatal EEG Sleep Stages Modelling by Temporal Profiles , 2007, EUROCAST.

[7]  D. Durand,et al.  Suppression and control of epileptiform activity by electrical stimulation: a review , 2001, Proc. IEEE.

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

[9]  A. Schulze-Bonhage,et al.  Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic , 2004 .

[10]  A. Schulze-Bonhage,et al.  Spatio-temporal patient–individual assessment of synchronization changes for epileptic seizure prediction , 2006, Clinical Neurophysiology.

[11]  Kaushik Majumdar.  Constraining Minimum-Norm Inverse by Phase Synchronization and Signal Power of the Scalp EEG Channels , 2009, IEEE Transactions on Biomedical Engineering.

[12]  Kaushik Majumdar,et al.  Differential operator in seizure detection , 2009, Comput. Biol. Medicine.

[13]  Brian Litt,et al.  Detection of seizure precursors from depth-EEG using a sign periodogram transform , 2003, IEEE Transactions on Biomedical Engineering.

[14]  J. Gotman,et al.  A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device , 1997, IEEE Transactions on Biomedical Engineering.

[15]  Xin Wang,et al.  Laplacian Operator-Based Edge Detectors , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Morikuni Takigawa,et al.  Developing of EEG Print and Its Preliminary Technical Application , 1994, The Japanese journal of psychiatry and neurology.

[17]  Malek Adjouadi,et al.  Seizure Detection: An Assessment of Time- and Frequency-Based Features in a Unified Two-Dimensional Decisional Space Using Nonlinear Decision Functions , 2009, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[18]  L. Tarassenko,et al.  Linear and non-linear methods for automatic seizure detection in scalp electro-encephalogram recordings , 2002, Medical and Biological Engineering and Computing.

[19]  C. Koch,et al.  Invariant visual representation by single neurons in the human brain , 2005, Nature.

[20]  Paul B. Colditz,et al.  A computer-aided detection of EEG seizures in infants: a singular-spectrum approach and performance comparison , 2002, IEEE Transactions on Biomedical Engineering.

[21]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[22]  P. Pardalos,et al.  Performance of a seizure warning algorithm based on the dynamics of intracranial EEG , 2005, Epilepsy Research.

[23]  R. Kass,et al.  Multiple neural spike train data analysis: state-of-the-art and future challenges , 2004, Nature Neuroscience.

[24]  Patrick E. McSharry,et al.  Comparison of predictability of epileptic seizures by a linear and a nonlinear method , 2003, IEEE Transactions on Biomedical Engineering.

[25]  R.D. Jones,et al.  Enhancement of deep epileptiform activity in the EEG via 3-D adaptive spatial filtering , 1999, IEEE Transactions on Biomedical Engineering.

[26]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[27]  Andrew M. White,et al.  Efficient unsupervised algorithms for the detection of seizures in continuous EEG recordings from rats after brain injury , 2006, Journal of Neuroscience Methods.

[28]  David J. Hand,et al.  ROC Curves for Continuous Data , 2009 .

[29]  H. Piaggio.  Mathematical Analysis , 1955, Nature.