Morphological descriptors for automatic detection of epileptiform events
| Autor: | Christine Fredel Boos, Fernando Mendes de Azevedo, Maria do Carmo Vitarelli Pereira, Fernanda Isabel Marques Argoud |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Brain Mapping
Electronic Data Processing Epilepsy Time Factors Artificial neural network medicine.diagnostic_test business.industry Computer science Electroencephalography Signal Processing Computer-Assisted Pattern recognition Morphological descriptors Neurophysiology medicine.disease Sensitivity and Specificity medicine Humans Neural Networks Computer Artificial intelligence Entropy (energy dispersal) business Algorithms |
| Zdroj: | 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. |
| Popis: | The purpose of this study was to analyze morphological characteristics of electroencephalogram (EEG) signals in order to define a representation of epileptiform events that can distinguish them from other events occurring in the signal. There are several studies on parameterization of EEG signals, particularly for automatic detection of paroxysms related to epilepsy. Considering that during the automatic detection process the morphological characteristics pertaining to these events may get mixed up if only conventional descriptors are used, it was necessary to create a new set of parameters that reveal more differences between them. The parameters are fed to artificial neural networks and the individual and collective contribution of each parameter was evaluated by statistical process. The proposed method achieved a success rate of 80-90%, sensitivity and specificity between 85% and 96%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|