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

► Automatic detection of HFOs is necessary to bring the analysis of HFOs into clinical practice in presurgical evaluation of epilepsy. ► An artificial neural network based detector of ripple HFOs is presented, which incorporates human expertise to separate ripple HFOs from background activity. ► The presented automatic detector allows the delineation of brain areas with high ripple HFO counts as an indicator of the seizure onset zone.