A computer-aided detection of EEG seizures in infants: a singular-spectrum approach and performance comparison

Presents a scalp electroencephalogram (EEG) seizure detection scheme based on singular spectrum analysis (SSA) and Rissanen minimum description length (MDL) model-order selection (SSA-MDL). Preprocessing of the signals allows for the drastic reduction of the number of false alarms. Statistical performance comparison with seizure detection schemes of Gotman et al. (1997) and Liu et al. (1992) is performed on both synthetic data and real EEG seizures. Monte Carlo simulations based on synthetic infant EEG seizure data reveals some detection drawbacks on a large variety of seizure waveforms. Detection using both Monte Carlo and four real infant scalp EEG signals shows the superiority of the SSA-MDL method with an average good detection rate of >93% and false detection rate <4%.

[1]  W. J. Williams,et al.  Cross Time-frequency Representation Of Electrocorticograms In Temporal Lobe Epilepsy , 1991 .

[2]  David Popivanov,et al.  Method for single-trial readiness potential identification, based on singular spectrum analysis , 1996, Journal of Neuroscience Methods.

[3]  J. Volpe.  Neurology of the Newborn , 1959, Major problems in clinical pediatrics.

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

[5]  W. J. Williams,et al.  Time-frequency representation of electrocorticograms in temporal lobe epilepsy , 1992, IEEE Transactions on Biomedical Engineering.

[6]  L Ingber,et al.  Statistical mechanics of neocortical interactions: multiple scales of EEG. , 1996, Electroencephalography and clinical neurophysiology. Supplement.

[7]  C. Elger,et al.  Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss. , 1995, Electroencephalography and clinical neurophysiology.

[8]  Paul B. Colditz,et al.  Nonlinear nonstationary Wiener model of infant EEG seizures , 2002, IEEE Transactions on Biomedical Engineering.

[9]  Paul B. Colditz,et al.  Time-varying statistical complexity measures with application to EEG analysis and segmentation , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  P Celka,et al.  Time-varying statistical dimension analysis with application to newborn scalp EEG seizure signals. , 2002, Medical engineering & physics.

[11]  J. Gotman,et al.  Evaluation of an automatic seizure detection method for the newborn EEG. , 1997, Electroencephalography and clinical neurophysiology.

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

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

[14]  F. H. Lopes da Silva,et al.  Model of brain rhythmic activity , 1974, Kybernetik.

[15]  P. Rapp,et al.  Re-examination of the evidence for low-dimensional, nonlinear structure in the human electroencephalogram. , 1996, Electroencephalography and clinical neurophysiology.

[16]  Hediger,et al.  Fractal dimension and local intrinsic dimension. , 1989, Physical review. A, General physics.

[17]  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.

[18]  G. Holmes,et al.  Prognostic value of the electroencephalogram in term and preterm infants following neonatal seizures. , 1985, Electroencephalography and clinical neurophysiology.

[19]  Mees,et al.  Singular-value decomposition and embedding dimension. , 1987, Physical review. A, General physics.

[20]  R. Vautard,et al.  Singular-spectrum analysis: a toolkit for short, noisy chaotic signals , 1992 .

[21]  R. Hornero,et al.  Estimating complexity from EEG background activity of epileptic patients. , 1999, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[22]  Jean-Marc Vesin,et al.  Observer of autonomic cardiac outflow based on blind source separation of ECG parameters , 2000, IEEE Transactions on Biomedical Engineering.

[23]  Jorma Rissanen,et al.  Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

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

[25]  G. P. King,et al.  Extracting qualitative dynamics from experimental data , 1986 .

[26]  J. Gotman.  Automatic seizure detection: improvements and evaluation. , 1990, Electroencephalography and clinical neurophysiology.

[27]  Piotr J. Franaszczuk,et al.  Epileptic seizures are characterized by changing signal complexity , 2001, Clinical Neurophysiology.

[28]  R. Vetter.  Extraction of efficient and characteristic features of multidimensional time series : application to the human cardiovascular system , 1999 .

[29]  Thomas Kailath,et al.  Detection of signals by information theoretic criteria , 1985, IEEE Trans. Acoust. Speech Signal Process..

[30]  G. Bergey,et al.  Time-frequency analysis using the matching pursuit algorithm applied to seizures originating from the mesial temporal lobe. , 1998, Electroencephalography and clinical neurophysiology.

[31]  Jean Gotman,et al.  Automatic seizure detection in newborns and infants , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[32]  Ivan Dvořák,et al.  Singular-value decomposition in attractor reconstruction: pitfalls and precautions , 1992 .

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