Exploiting Feature Selection and Neural Network Techniques for Identification of Focal and Nonfocal EEG Signals in TQWT Domain

For drug resistance patients, removal of a portion of the brain as a cause of epileptic seizures is a surgical remedy. However, before surgery, the detailed analysis of the epilepsy localization area is an essential and logical step. The Electroencephalogram (EEG) signals from these areas are distinct and are referred to as focal, while the EEG signals from other normal areas are known as nonfocal. The visual inspection of multiple channels for detecting the focal EEG signal is time-consuming and prone to human error. To address this challenge, we propose a novel method based on differential operator and Tunable Q-factor wavelet transform (TQWT) to distinguish the focal and nonfocal signals. For this purpose, first, the EEG signal was differenced and then decomposed by TQWT. Second, several entropy-based features were derived from the TQWT subbands. Third, the efficacy of the six binary feature selection algorithms, binary bat algorithm (BBA), binary differential evolution (BDE) algorithm, firefly algorithm (FA), genetic algorithm (GA), grey wolf optimization (GWO), and particle swarm optimization (PSO), was evaluated. In the end, the selected features were fed to several machine learning and neural network classifiers. We observed that the PSO with neural networks provides an effective solution for the application of focal EEG signal detection. The proposed framework resulted in an average classification accuracy of 97.68%, a sensitivity of 97.26%, and a specificity of 98.11% in a tenfold cross-validation strategy, which is higher than the state of the art used in the public Bern-Barcelona EEG database.

Clinical Validation of the Champagne Algorithm for Epilepsy Spike Localization

Magnetoencephalography (MEG) is increasingly used for presurgical planning in people with medically refractory focal epilepsy. Localization of interictal epileptiform activity, a surrogate for the seizure onset zone whose removal may prevent seizures, is challenging and depends on the use of multiple complementary techniques. Accurate and reliable localization of epileptiform activity from spontaneous MEG data has been an elusive goal. One approach toward this goal is to use a novel Bayesian inference algorithm—the Champagne algorithm with noise learning—which has shown tremendous success in source reconstruction, especially for focal brain sources. In this study, we localized sources of manually identified MEG spikes using the Champagne algorithm in a cohort of 16 patients with medically refractory epilepsy collected in two consecutive series. To evaluate the reliability of this approach, we compared the performance to equivalent current dipole (ECD) modeling, a conventional source localization technique that is commonly used in clinical practice. Results suggest that Champagne may be a robust, automated, alternative to manual parametric dipole fitting methods for localization of interictal MEG spikes, in addition to its previously described clinical and research applications.

Magnetoencephalography in Alzheimer Disease

There are two basic ways Magnetoencephalography (MEG) has been applied. The most typical way is recording brain signals related to specific stimuli and tasks or signals indicative of focal pathology as in presurgical brain mapping and epilepsy localization. The second way is recording patterns of spontaneous activity characteristic of particular states or traits. An example of the latter application is described in this chapter that details efforts of deriving brain activity patterns characteristic of Alzheimer’s dementia. The derivation of such patterns will be of great value in diagnosis, prognosis, as well as monitoring progress (or the process of amelioration) of diseases.

P5677Ictal asystole and bradycardia patients with epilepsy

Background Events of ictal bradycardia or asystole may be of importance in epilepsy patients showing with ictal falls and are a funder to SUDEP. With using implantable loop recorders, we can detect ictal bradycardia or asystole. And implantation of cardiac pacemakers may prevent life-threatening syncope, cardiac arrest, and disturbances. Purpose The purpose of this study is to look at how many ictal bradycardia or asystole and match with localization, types of seizure and antiepileptic drugs in a patient with hard to treat epilepsy. Methods Patients with hard to treat epilepsy were implanted loop recorders. Patients or their relations were activated loop recorder (with a special patient assistant) during or after seizure depending on the type of seizure. Results 204 patients included in the study. The mean duration of loop recording 24 months. 1168 ECG seizure were reordered of 204 patients, 494 (42%) secondary generalized seizures and 674 (58%) partial seizures. Nine patients (4%) were recorded ictal bradycardia and ictal asystole. Only four patients with ictal asystole and bradycardia take AED (antiepileptic drug) inhibit sodium channels. During seizure were recorded only 14 (1, 1%) seizure with ictal asystole and bradycardia of nine patients, 6 (42%) – with ictal asystole (5 – SA-block, 1 – AV-block), 8 (57%) – ictal bradycardia. Ten (71%) events of 14 was secondary generalized seizures, 4 (28%) - partial seizures. Five ictal asystoles recorded during secondarily generalized seizures, and only 1 partial seizure. Five ictal bradycardias reordered during secondarily generalized seizures, 3 - partial seizure. Frontal-temporal localization only 4 patients, 1 – occipital-frontal, 1 – frontal, 3 – without consistent epilepsy localization. Three patients with bilateral lateralization, 2 – left lateralization, 1 – right lateralization, 3 – without consistent epilepsy lateralization. Conclusions Ictal asystole can be problematic to diagnose because of both its under-recognition and its appearance only during seizures. In this study, we showed the most life-threatening events occurred in patients with the secondarily generalized seizures. Bradyarrhythmias can one of possible sudden unexplained death in epilepsy patients (SUDEP). No clear association was seen between ictal bradycardia/asystole and lateralization or localization of seizure onset.