Block term decomposition for modelling epileptic seizures
- PDF / 3,276,232 Bytes
- 19 Pages / 595 x 794 pts Page_size
- 58 Downloads / 172 Views
RE SE A RCH
Open Access
Block term decomposition for modelling epileptic seizures Borbála Hunyadi1,2* , Daan Camps1 , Laurent Sorber1,3,2 , Wim Van Paesschen4,5 , Maarten De Vos6,7 , Sabine Van Huffel1,2 and Lieven De Lathauwer1,2,8 Abstract Recordings of neural activity, such as EEG, are an inherent mixture of different ongoing brain processes as well as artefacts and are typically characterised by low signal-to-noise ratio. Moreover, EEG datasets are often inherently multidimensional, comprising information in time, along different channels, subjects, trials, etc. Additional information may be conveyed by expanding the signal into even more dimensions, e.g. incorporating spectral features applying wavelet transform. The underlying sources might show differences in each of these modes. Therefore, tensor-based blind source separation techniques which can extract the sources of interest from such multiway arrays, simultaneously exploiting the signal characteristics in all dimensions, have gained increasing interest. Canonical polyadic decomposition (CPD) has been successfully used to extract epileptic seizure activity from wavelet-transformed EEG data (Bioinformatics 23(13):i10–i18, 2007; NeuroImage 37:844–854, 2007), where each source is described by a rank-1 tensor, i.e. by the combination of one particular temporal, spectral and spatial signature. However, in certain scenarios, where the seizure pattern is nonstationary, such a trilinear signal model is insufficient. Here, we present the application of a recently introduced technique, called block term decomposition (BTD) to separate EEG tensors into rank-(Lr , Lr , 1) terms, allowing to model more variability in the data than what would be possible with CPD. In a simulation study, we investigate the robustness of BTD against noise and different choices of model parameters. Furthermore, we show various real EEG recordings where BTD outperforms CPD in capturing complex seizure characteristics. 1 Introduction Epilepsy is one of the most common neurological disorders, affecting 0.5% to 1% of the global population [1]. The clinical manifestation of this disease is the epileptic seizure, arising from the abnormal, synchronous electrical activity of a large network of neurons. As such, seizure activity can be recorded using electroencephalogram (EEG), which is currently one of the most important modalities for epilepsy diagnosis and monitoring [2]. However, visual analysis of EEG is often challenging and time consuming, due to several types of artefacts which may be superimposed on the pattern of interest (i.e. ictal activity) and due to the large amount of data resulting from long-term EEG monitoring. Therefore, automatic techniques which are capable of extracting relevant *Correspondence: [email protected] 1 STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Department of Electrical Engineering, KU Leuven, 3001 Leuven, Belgium 2 iMinds Medical IT Department, 3001 Leuven, Belgium Full list of author information is available at the en
Data Loading...
