Threshold based MEG data classification for healthy and epileptic subjects

摘要

The most commonly used clinical tool for initial diagnosis of epilepsy is electroencephalogram (EEG). Recent advances in magnetoencephalography (MEG) technology provide a new source of information to analyze brain activities. In order to determine whether or not particular subjects' brain signals exhibit epileptic activities, epileptologists often spend considerable amount of time to review MEG recordings. This paper proposes a new algorithm for automatic classification of MEG data into two classes: data that belongs to healthy subjects and data that belongs to epileptic subjects. The classifier makes use of energy values of Delta and Theta bands. The effectiveness of proposed classifier has been tested using real MEG data obtained from 35 healthy subjects and 35 epileptic patients. Results obtained from the classifier show that the proposed classifier can be used as a tool in the initial diagnosis phase of epilepsy.