Automatic 80–250 Hz “ripple” high frequency oscillation detection in invasive subdural grid and strip recordings in epilepsy by a radial basis function neural network

Abstract

ObjectiveRecent studies give evidence that high frequency oscillations (HFOs) in the range between 80Hz and 500Hz in invasive recordings of epilepsy patients have the potential to serve as reliable markers of epileptogenicity. This study presents an algorithm for automatic HFO detection. MethodsThe presented HFO detector uses a radial basis function neural network. Input features of the detector were energy, line length and instantaneous frequency. Visual marked “ripple” HFOs (80–250Hz) of 3 patients were used to train the neural network, and a further 8 patients served for the detector evaluation. ResultsDetector sensitivity and specificity were 49.1% and 36.3%. The linear and rank correlation between visual and automatic marked “ripple” HFO counts over the channels were significant for all recordings. A reference detector based on the line length achieved a sensitivity of 35.4% and a specificity of 46.8%. ConclusionsAutomatic detections corresponded only partly to visual markings for single events but the relative distribution of brain regions displaying “ripple” HFO activity is reflected by the automated system. SignificanceThe detector allows the automatic evaluation of brain areas with high HFO frequency, which is of high relevance for the demarcation of the epileptogenic zone.