Segmentation and classification of EEG during epileptic seizures

Abstract

We present a method for the automatic comparison of epileptic seizures in EEG, allowing the grouping of seizures having similar overall patterns. Each channel of the EEG is first broken down into segments having relatively stationary characteristics. Features are then calculated for each segment and all segments of all channels of the seizures of one patient are grouped into clusters of similar morphology. This clustering allows labeling of every EEG segment. Methods derived from string matching procedures are then used to obtain an overall edit distance between two seizures, a distance that represents how the two seizures, taken in their entirety and including the channels not actually involved in the discharge, resemble each other. Examples from 5 patients, 3 with intracerebral electrodes and two with scalp electrodes, illustrate the ability of the method to group seizures of similar morphology.