In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained. © 2015 IEEE.
Learning Vector Quantization and Permutation Entropy to Analyse Epileptic Electroencephalography / Mammone, N.; Duun-Henriksen, J.; Kjaer, T. W.; Campolo, M.; La Foresta, F.; Morabito, C.. - 2015:(2015). (Intervento presentato al convegno IJCNN 2015 - International Joint Conference on Neural Networks tenutosi a Killarney, Ireland nel 12-17 July 2015) [10.1109/IJCNN.2015.7280615].
Learning Vector Quantization and Permutation Entropy to Analyse Epileptic Electroencephalography
N. Mammone;M. Campolo;F. La Foresta;C. Morabito
2015-01-01
Abstract
In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained. © 2015 IEEE.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
