Fast Automatic Localization of Epileptic Seizure Onset Zones Using Complex Morlet Wavelet Transform-based Singular Value Decomposition

A new method for localization of epileptic seizure onset zones (SOZs) is proposed, which uses the Shannon-entropy-based complex Morlet wavelet transform to extract a satisfactory time-frequency feature of high-frequency oscillations (HFOs). The singular value decomposition and the K-medoids clustering algorithm are employed to extract effective features from the redundant matrix of wavelet coefficients. A distinctive feature is to use the singular values to detect HFOs with the consideration that the singular values of HFOs are generally significantly higher than those of normal case. Based on the half-maximum method, the localization of SOZs are achieved by using the characteristics of HFOs. Comparisons show that our method provides a higher sensitivity and specificity than two existing methods do.

[1]  P. Hilfiker,et al.  P795: Human intracranial high frequency oscillations (HFOs) detected by automatic time-frequency analysis , 2014, Clinical Neurophysiology.

[2]  Min Wu,et al.  Fast, Accurate Localization of Epileptic Seizure Onset Zones Based on Detection of High-Frequency Oscillations Using Improved Wavelet Transform and Matching Pursuit Methods , 2017, Neural Computation.

[3]  Peter W. Tse,et al.  Development of an advanced noise reduction method for vibration analysis based on singular value decomposition , 2003 .

[4]  Gregory K. Bergey,et al.  Identification of seizure onset zone and preictal state based on characteristics of high frequency oscillations , 2015, Clinical Neurophysiology.

[5]  J. Sarnthein,et al.  Human Intracranial High Frequency Oscillations (HFOs) Detected by Automatic Time-Frequency Analysis , 2014, PloS one.

[6]  Jan Cimbálník,et al.  The CS algorithm: A novel method for high frequency oscillation detection in EEG , 2018, Journal of Neuroscience Methods.

[7]  M. Brenner.  Non-stationary dynamics data analysis with wavelet-SVD filtering , 2003 .

[8]  Jean Gotman,et al.  Interictal high-frequency oscillations (100-500 Hz) in the intracerebral EEG of epileptic patients. , 2007, Brain : a journal of neurology.

[9]  A. S. Malik,et al.  Epileptic seizure detection using the singular values of EEG signals , 2013, 2013 ICME International Conference on Complex Medical Engineering.

[10]  Jing Hu,et al.  Removal of EOG and EMG artifacts from EEG using combination of functional link neural network and adaptive neural fuzzy inference system , 2015, Neurocomputing.

[11]  M. Kemal Kiymik,et al.  Comparison of STFT and wavelet transform methods in determining epileptic seizure activity in EEG signals for real-time application , 2005, Comput. Biol. Medicine.

[12]  J. Gotman,et al.  High-frequency oscillations during human focal seizures. , 2006, Brain : a journal of neurology.

[13]  J. McNamara,et al.  Mechanism of epilepsy. , 1994, Annual review of medicine.

[14]  Hae-Sang Park,et al.  A simple and fast algorithm for K-medoids clustering , 2009, Expert Syst. Appl..

[15]  Xiongbo Wan,et al.  Automatic detection of high frequency oscillations based on Fuzzy entropy and Fuzzy neural network , 2016, CCC 2016.

[16]  J. Mixter.  Fast , 2012 .

[17]  Premysl Jiruska,et al.  Resection of individually identified high‐rate high‐frequency oscillations region is associated with favorable outcome in neocortical epilepsy , 2014, Epilepsia.

[18]  G. Worrell,et al.  Interictal high-frequency oscillations in focal human epilepsy. , 2016, Current opinion in neurology.

[19]  Laurent Albera,et al.  Automatic detection of fast ripples , 2013, Journal of Neuroscience Methods.

[20]  J. Jefferys,et al.  High‐frequency oscillations as a new biomarker in epilepsy , 2012, Annals of neurology.

[21]  Jinhua She,et al.  A four-stage localization method for epileptic seizure onset zones , 2017 .

[22]  J Gotman,et al.  Automatic seizure detection in SEEG using high frequency activities in wavelet domain. , 2013, Medical engineering & physics.