A nonparametric feature for neonatal EEG seizure detection based on a representation of pseudo-periodicity.

Automated methods of neonatal EEG seizure detection attempt to highlight the evolving, stereotypical, pseudo-periodic, nature of EEG seizure while rejecting the nonstationary, modulated, coloured stochastic background in the presence of various EEG artefacts. An important aspect of neonatal seizure detection is, therefore, the accurate representation and detection of pseudo-periodicity in the neonatal EEG. This paper describes a method of detecting pseudo-periodic components associated with neonatal EEG seizure based on a novel signal representation; the nonstationary frequency marginal (NFM). The NFM can be considered as an alternative time-frequency distribution (TFD) frequency marginal. This method integrates the TFD along data-dependent, time-frequency paths that are automatically extracted from the TFD using an edge linking procedure and has the advantage of reducing the dimension of a TFD. The reduction in dimension simplifies the process of estimating a decision statistic designed for the detection of the pseudo-periodicity associated with neonatal EEG seizure. The use of the NFM resulted in a significant detection improvement compared to existing stationary and nonstationary methods. The decision statistic estimated using the NFM was then combined with a measurement of EEG amplitude and nominal pre- and post-processing stages to form a seizure detection algorithm. This algorithm was tested on a neonatal EEG database of 18 neonates, 826 h in length with 1389 seizures, and achieved comparable performance to existing second generation algorithms (a median receiver operating characteristic area of 0.902; IQR 0.835-0.943 across 18 neonates).

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  B. Boashash,et al.  A Nonlinear Model of Newborn EEG with Nonstationary Inputs , 2010, Annals of Biomedical Engineering.

[3]  T. Inder,et al.  Seizure detection algorithm for neonates based on wave-sequence analysis , 2006, Clinical Neurophysiology.

[4]  L. D. de Vries,et al.  Amplitude integrated EEG 3 and 6 hours after birth in full term neonates with hypoxic–ischaemic encephalopathy , 1999, Archives of disease in childhood. Fetal and neonatal edition.

[5]  C J Stam,et al.  Neonatal Seizure Monitoring Using Non-Linear EEG Analysis , 2004, Neuropediatrics.

[6]  G. Boylan,et al.  Automated neonatal seizure detection , 2006, Clinical Neurophysiology.

[7]  Terrie Inder,et al.  Neonatal status epilepticus. , 2010, Seminars in pediatric neurology.

[8]  P. Peebles.  Probability, Random Variables and Random Signal Principles , 1993 .

[9]  Olivier J. J. Michel,et al.  Measuring time-Frequency information content using the Rényi entropies , 2001, IEEE Trans. Inf. Theory.

[10]  A. Legido,et al.  The Exact Ictal and Interictal Duration of Electroencephalographic Neonatal Seizures , 1987, Epilepsia.

[11]  G. Lightbody,et al.  Performance assessment for EEG-based neonatal seizure detectors , 2011, Clinical Neurophysiology.

[12]  J. Callaghan.  Medical engineering & physics. , 2005, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[13]  B. Boashash,et al.  Preprocessing and time-frequency analysis of newborn EEG seizures , 2001, IEEE Engineering in Medicine and Biology Magazine.

[14]  John M. O'Toole,et al.  Time-Frequency Detection of Slowly Varying Periodic Signals with Harmonics: Methods and Performance Evaluation , 2011, EURASIP J. Adv. Signal Process..

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

[16]  D B Vigneron,et al.  Seizure-associated brain injury in term newborns with perinatal asphyxia , 2002, Neurology.

[17]  Mj Martin Bastiaans.  Time-frequency signal analysis , 2008 .

[18]  Mostefa Mesbah,et al.  Modelling newborn EEG background using a time-Varying fractional Brownian process , 2007, 2007 15th European Signal Processing Conference.

[19]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[20]  Douglas L. Jones,et al.  Unitary equivalence: a new twist on signal processing , 1995, IEEE Trans. Signal Process..

[21]  Boualem Boashash,et al.  Kernel design for time-frequency signal analysis using the Radon transform , 1993, IEEE Trans. Signal Process..

[22]  E. Bedrosian.  A Product Theorem for Hilbert Transforms , 1963 .

[23]  A. Liu,et al.  Detection of neonatal seizures through computerized EEG analysis. , 1992, Electroencephalography and clinical neurophysiology.

[24]  David G. Stork,et al.  Pattern Classification , 1973 .

[25]  Simon Haykin,et al.  Advances in spectrum analysis and array processing , 1991 .

[26]  P. Plouin,et al.  Atlas of neonatal electroencephalography, éd, Stockard-Pope JE, Werner SS, Bickford RG. Raven Press, Paris (1992), 400 p. , 1992 .

[27]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[28]  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.

[29]  S. E. Rose,et al.  Seizures are associated with brain injury severity in a neonatal model of hypoxia–ischemia , 2010, Neuroscience.

[30]  M. De Vos,et al.  Validation of a new automated neonatal seizure detection system: A clinician’s perspective , 2011, Clinical Neurophysiology.

[31]  A. Aarabi,et al.  A multistage knowledge-based system for EEG seizure detection in newborn infants , 2007, Clinical Neurophysiology.

[32]  Mostefa Mesbah,et al.  A Nonstationary Model of Newborn EEG , 2007, IEEE Transactions on Biomedical Engineering.

[33]  S. Huffel,et al.  Automated neonatal seizure detection mimicking a human observer reading EEG , 2008, Clinical Neurophysiology.

[34]  Mostefa Mesbah,et al.  Seizure detection of newborn EEG using a model-based approach , 1998, IEEE Transactions on Biomedical Engineering.

[35]  B. Boashash,et al.  Quadratic time-frequency distribution selection for seizure detection in the newborn , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[36]  Ljubisa Stankovic,et al.  Time–frequency-based detection of fast manoeuvring targets , 2010 .

[37]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

[38]  R B Reilly,et al.  Classifier models and architectures for EEG-based neonatal seizure detection , 2008, Physiological measurement.

[39]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[40]  Lionel Carmant,et al.  Neonatal seizures: do they damage the brain? , 2009, Pediatric neurology.

[41]  Patrick Flandrin,et al.  A time-frequency formulation of optimum detection , 1988, IEEE Trans. Acoust. Speech Signal Process..

[42]  Ronald N. Bracewell,et al.  The Fourier Transform and Its Applications , 1966 .

[43]  G. Lightbody,et al.  EEG-based neonatal seizure detection with Support Vector Machines , 2011, Clinical Neurophysiology.

[44]  J. Frost,et al.  A Multistage System for the Automated Detection of Epileptic Seizures in Neonatal Electroencephalography , 2009, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[45]  Aly A. Farag,et al.  Edge linking by sequential search , 1995, Pattern Recognit..

[46]  Mostefa Mesbah,et al.  IF estimation for multicomponent signals using image processing techniques in the time-frequency domain , 2007, Signal Process..

[47]  Boualem Boashash,et al.  The bootstrap and its application in signal processing , 1998, IEEE Signal Process. Mag..

[48]  Gordon Lightbody,et al.  An evaluation of automated neonatal seizure detection methods , 2005, Clinical Neurophysiology.