Entropy spatial clustering in epileptic EEG

Nadia Mammone, Giuseppina Inuso, Fabio La Foresta, Mario Versaci, Francesco C. Morabito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Works in literature analyse neuronal electrical source distribution on human brain cortex from noninvasive measurements of electric potentials at multichannel scalp electrodes (Electroencephalography). In this paper a new technique, based on entropy, is introduced to study the synchronization of the electric activity of neuronal sources in the brain. An abnormal synchronization (abnormal interactions between the electrodes) can result in an epileptic seizure and Renyi's entropy topography and its spatial clustering are proposed to measure this interaction and to provide a spatial picture of its distribution over the cortex. Three EEG dataset from patients affected by partial epilepsy were analysed. Entropy showed a very steady spatial distribution and a clear relationship with the region of seizure onset. Entropy mapping was compared with the standard power mapping that was much less stable and selective. A SOM based spatial clustering of entropy topography showed that the critical electrodes were coupled together long time before the seizure onset.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1981-1986
Number of pages6
DOIs
Publication statusPublished - 2009
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
Duration: Jun 14 2009Jun 19 2009

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
CountryUnited States
CityAtlanta, GA
Period6/14/096/19/09

Keywords

  • Electroencephalography
  • Epilepsy
  • Renyi's entropy
  • SOM

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Entropy spatial clustering in epileptic EEG'. Together they form a unique fingerprint.

Cite this