Model-Based Spike Detection of Epileptic EEG Data

Abstract

Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

Interictal epileptiform discharge characteristics underlying expert interrater agreement

“…Some previous studies have applied nonlinear energy operator (NLEO) for IED detection purposes (Mukhopadhyay and Ray, 1998; Liu et al, 2013; Bagheri et al, 2016). The NLEO is computed as: $${\phi }_k\{\mathrm{x}[\mathrm{n}]\}={\mathrm{normalx}}^2[\mathrm{n}]-\mathrm{x}[\mathrm{n}-\mathrm{k}]\mathrm{x}[\mathrm{n}+\mathrm{k}],$$where the resolution parameter k (Choi and Kim, 2002) is chosen to have values in the range of 1–40.…”

A retrospective glance at automatic detection of epileptic spike in electroencephalogram

“…Other researches do not give specific information of the length of the data segments. Under this circumstance, the outcomes are evaluated using sensitivity, specificity and selectivity, or even accuracy in one case (24). Eleven cases demonstrate both detection rate (sensitivity) and false detection rate (selectivity) accurately.…”

“…It is computed as the ratio of the absolute amplitude of the wave to the background amplitude, which is defined as the average amplitude of a period adjacent or around the event (21). Other commonly used morphological traits are duration, amplitude, slope and sharpness of the wave or half wave (4,11,(22)(23)(24). Context information, statistical measurement can also be used to develop features for robustness reason (23,25,26).…”

Fast and efficient rejection of background waveforms in interictal EEG

“…In addition, several other methods have been reported more recently [3, 4, 5, 6]. These methods use template matching in combination with clustering [3], template matching in combination with support vector machines (SVMs) [4], nonlinear energy operator in conjunction with mimetic analysis and Adaboost classifiers [5], and sequence merging followed by SVMs [6]. However, the common problem with these methods is the lack of a sizable database of different ET profiles to validate the performance of the ET detection systems.…”