Clustering Approach to Quantify Long-Term Spatio-Temporal Interactions in Epileptic Intracranial Electroencephalography

Abnormal dynamical coupling between brain structures is believed to be primarily responsible for the generation of epileptic seizures and their propagation. In this study, we attempt to identify the spatio-temporal interactions of an epileptic brain using a previously proposed nonlinear dependency measure. Using a clustering model, we determine the average spatial mappings in an epileptic brain at different stages of a complex partial seizure. Results involving 8 seizures from 2 epileptic patients suggest that there may be a fixed pattern associated with regional spatio-temporal dynamics during the interictal to pre-post-ictal transition.

[1]  KeoghEamonn,et al.  Clustering of time-series subsequences is meaningless , 2005 .

[2]  Theiler,et al.  Generating surrogate data for time series with several simultaneously measured variables. , 1994, Physical review letters.

[3]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[4]  M. Kaminski,et al.  Granger causality and information flow in multivariate processes. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  Jose C. Principe,et al.  Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM , 1999 .

[6]  Jitendra Malik,et al.  Contour and Texture Analysis for Image Segmentation , 2001, International Journal of Computer Vision.

[7]  A. N. Sharkovskiĭ.  Dynamic systems and turbulence , 1989 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation (3rd Edition) , 2007 .

[9]  Schreiber,et al.  Measuring information transfer , 2000, Physical review letters.

[10]  J.C. Principe,et al.  Synchronization analysis of epileptic ECOG data using SOM-based SI measure , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  P. Grassberger,et al.  A robust method for detecting interdependences: application to intracranially recorded EEG , 1999, chao-dyn/9907013.

[12]  Joaquín Fernández-Valdivia,et al.  A dynamic approach for clustering data , 1995, Signal Process..

[13]  Leonidas D. Iasemidis,et al.  Spatiotemporal dynamics of human epileptic seizures , 1996 .

[14]  J. Sackellares,et al.  Time dependencies in the occurrences of epileptic seizures , 1994, Epilepsy Research.

[15]  Schreiber,et al.  Improved Surrogate Data for Nonlinearity Tests. , 1996, Physical review letters.

[16]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[17]  V. Kvasnicka,et al.  Neural and Adaptive Systems: Fundamentals Through Simulations , 2001, IEEE Trans. Neural Networks.

[18]  Deniz Erdogmus,et al.  SOM-based similarity index measure: quantifying interactions between multivariate structures , 2003, 2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718).

[19]  Leonidas D. Iasemidis,et al.  Quadratic Binary Programming and Dynamical System Approach to Determine the Predictability of Epileptic Seizures , 2001, J. Comb. Optim..

[20]  J.C. Principe,et al.  Spatio-Temporal Clustering of Epileptic ECOG , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[21]  Deniz Erdogmus,et al.  Quantifying spatio-temporal dependencies in epileptic ECOG , 2005, Signal Process..

[22]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[23]  Eamonn J. Keogh,et al.  Clustering of time-series subsequences is meaningless: implications for previous and future research , 2004, Knowledge and Information Systems.