Automatic detection of the seizure onset zone based on ictal EEG

Abstract

In this paper we show a proof of concept for novel automatic seizure onset zone detector. The proposed approach utilizes the Austrian Institute of Technology (AIT) seizure detection system EpiScan extended by a frequency domain source localization module. EpiScan was proven to detect rhythmic epileptoform seizure activity often seen during the early phase of epileptic seizures with reasonable high sensitivity and specificity. Additionally, the core module of EpiScan provides complex coefficients and fundamental frequencies representing the rhythmic activity of the ictal EEG signal. These parameters serve as input to a frequency domain version of the Minimum Variance Beamformer to estimate the most dominant source. The position of this source is the detected seizure onset zone. The results are compared to a state of the art wavelet transformation approach based on a manually chosen frequency band. Our first results are encouraging since they coincide with those obtained with the wavelet approach and furthermore show excellent accordance with the medical report for the majority of analyzed seizures. In contrast to the wavelet approach our method has the advantage that it does not rely on a manual selection of the frequency band.

Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy

“…However, the generalizability of such single biomarkers has been insufficient for clinical practice [Nonoda 2016, Sinha 2017, Holler 2015, Cimbalnik 2017], primarily because of inter-patient variability, and it appears that one biomarker may not be sufficient to identify SOZs in all patients. While there have been multiple attempts to automate SOZ localization [Liu 2016, Graef 2013, Gritsch 2011], very little work has attempted to improve localization potential by means of combining multiple biomarkers. This exploratory study shows that combining multiple interictal electrophysiological biomarkers within a rigorous, supervised machine learning setting can be more accurate in performing interictal SOZ localization than can utilization of a single biomarker, essentially by reducing inter-patient variability.…”

Beamforming applied to surface EEG improves ripple visibility

“…Another application of beamforming is the rejection of artefacts and reconstruction of sources in EEG-fMRI (Brookes et al, 2008(Brookes et al, , 2009 and in MEG (Adjamian et al, 2009;Hillebrand et al, 2013). It has been shown that beamforming can also be used to localize epileptic spikes (Van Drongelen et al, 1996), and to localize ictal EEG activity (Gritsch et al, 2011), although dipole models or other distributed source models are more commonly used to localize spike activity (Plummer et al, 2008). One study used beamforming to reconstruct EEG signals, so-called virtual electrodes, at the same position as the actual electrodes, and showed an increased SNR and enhanced spike visibility in the virtual electrodes (Ward et al, 1999).…”