Unsupervised Classification of EEG from Subdural Seizure Recordings

Whereas the visual EEG-inspection of epileptic seizures draws the attention to the waxing and waning of specific graphoelements in multi-channel recordings, the domain of computerized EEG-analysis for epilepsy diagnosis is detection of transients (i.e., spikes) and the quantification of background activity (i.e., mapping procedures). We present an approach to identify relatively fast changes of background activity by use of an automatic classifier. This algorithm is independent of the occurrence of any specific single type of graphoelement. The EEG is segmentated into short epochs of 0.64 sec duration each. For every segment a set of parameters (Hjorth, spectral power in classical frequency bands) is extracted, which taken together build elements of a vector-space. The elements are clustered in an automatic and unsupervised manner by use of a cosine-classifier, such that every EEG-epoch belongs to one class. Changes of brain activity as seen with the EEG are marked by transitions from one class to another. The class occurrence density is defined as the number of different classes that occur within a pre-defined number of EEG-epochs. It gives a new measure of variability of the EEG-signal. Comparing the epochs when class transitions take place in different channels, the class transitions coincidence between two channels is a measure of functional coupling of brain areas.