Electroencephalography (EEG) and magnetoencephalography (MEG) are indispensable tools used in the diagnostic and treatment of epilepsy. They measure signais that display events heavily linked to epilepsy: the epileptic spikes. Thèse spikes are used by neurologists to confirm their diagnosis but aiso to localize the région of the brain that causes the pathology. Since current source localization techniques require a high signal to noise ratio (SNR), it is a common practice to average recordings which are assumed to contain similar events. However, how can we be sure the signais are similar enough to be averaged? The answer is to classify the spikes prior to signal averaging.
In the présent work, we présent the conception, methodology, and évaluation of a new classification technique based on the source représentation of epileptic spikes. Because the source space is used to classify the spikes, the method is able to separate spikes with similar morphologies but generated by différent sources. The performance of this algorithm was evaluated using simulated EEG and MEG signais. The results indicate that the method is able to group spikes with similar source représentation even if their morphologies are similar. When applied to real data, the method allowed us to identify new active régions of the brain when compared to traditional analysis.
| Date | 4 Jan 2010 |
|---|
| Original language | French |
|---|
| Awarding Institution | - École de technologie supérieure
|
|---|
| Supervisor | Jean-Marc Lina (Supervisor) |
|---|
Deslauriers-Gauthier, S. (Author),
Lina (Supervisor),
4 Jan 2010Student thesis: Master's thesis › Master in Engineering: Electrical Engineering