Epileptic Epileptic Electroencephalogram Research Articles

Online Learning Koopman Operator for Closed-Loop Electrical Neurostimulation in Epilepsy.

Electrical neuromodulation as a palliative treatment has been increasingly used in the control of epilepsy. However, current neuromodulations commonly implement predetermined actuation strategies and lack the capability of self-adaptively adjusting stimulation inputs. In this work, rooted in optimal control theory, we propose a Koopman-MPC framework for real-time closed-loop electrical neuromodulation in epilepsy, which integrates i) a deep Koopman operator based dynamical model to predict the temporal evolution of epileptic electroencephalogram (EEG) with an approximate finite-dimensional linear dynamics and ii) a model predictive control (MPC) module to design optimal seizure suppression strategies. The Koopman operator based linear dynamical model is embedded in the latent state space of the autoencoder neural network, in which we can approximate and update the Koopman operator online. The linear dynamical property of the Koopman operator ensures the convexity of the optimization problem for subsequent MPC control. The proposed deep Koopman operator model shows greater predictive capability than the baseline models (e.g., vector autoregressive model, kernel based method and recurrent neural network (RNN)) in both synthetic and real epileptic EEG data. Moreover, compared with the RNN-MPC framework, our Koopman-MPC framework can suppress seizure dynamics with better computational efficiency in both the Jansen-Rit model and the Epileptor model. Koopman-MPC framework opens a new window for model-based closed-loop neuromodulation and sheds light on nonlinear neurodynamics and feedback control policies.

EEG Microstate Features as an Automatic Recognition Model of High-Density Epileptic EEG Using Support Vector Machine.

Epilepsy is one of the most serious nervous system diseases; it can be diagnosed accurately by video electroencephalogram. In this study, we analyzed microstate epileptic electroencephalogram (EEG) to aid in the diagnosis and identification of epilepsy. We recruited patients with focal epilepsy and healthy participants from the Third Xiangya Hospital and recorded their resting EEG data. In this study, the EEG data were analyzed by microstate analysis, and the support vector machine (SVM) classifier was used for automatic epileptic EEG classification based on features of the EEG microstate series, including microstate parameters (duration, occurrence, and coverage), linear features (median, second quartile, mean, kurtosis, and skewness) and non-linear features (Petrosian fractal dimension, approximate entropy, sample entropy, fuzzy entropy, and Lempel-Ziv complexity). In the gamma sub-band, the microstate parameters as a model were the best for interictal epilepsy recognition, with an accuracy of 87.18%, recall of 70.59%, and an area under the curve of 94.52%. There was a recognition effect of interictal epilepsy through the features extracted from the EEG microstate, which varied within the 4~45 Hz band with an accuracy of 79.55%. Based on the SVM classifier, microstate parameters and EEG features can be effectively used to classify epileptic EEG, and microstate parameters can better classify epileptic EEG compared with EEG features.

Epileptic EEG Signal Classification Using Convolutional Neural Network Based on Multi-Segment of EEG Signal

High performance in the epileptic electroencephalogram (EEG) signal classification is an important step in diagnosing epilepsy. Furthermore, this classification is carried out to determine whether the EEG signal from a person's examination results is categorized as an epileptic signal or not (healthy). Several automated techniques have been proposed to assist neurologists in classifying these signals. In general, these techniques have yielded a high average accuracy in classification, but the performance still needs to be improved. Therefore, we propose a convolutional neural network based on multi-segment of EEG signals to classify epileptic EEG signals. This method is built to overcome data limitations in the convolutional neural network training process and add the ensemble combination process. The multi-segment of EEG signal is formed by splitting the signal without overlapping each channel and converting it into the spectrogram image based on the short-time Fourier transform value. The spectrogram image is then used as input for the convolutional neural network in in-depth training and testing. The convolutional neural network model of the training results is used to classify each EEG signal segment on each test channel before entering the ensemble combination stage for the final classification. To evaluate the performance of our proposed method, we used the Bonn EEG dataset. The dataset consists of five EEG records labelled as A, B, C, D, and E. The experiments on several datasets (AB-C, AB-D, AB-E, AB-CD, AB-CDE, and AB-CD-E) which were arranged from the dataset showed that our proposed method (with segment) performs better than without segment. Our proposed method yielded the best average of classification accuracy which is 99.33%, 100%, 100%, 99.5%, 99.8%, and 99.4% for the AB-C, AB-D, AB-E, AB-CD, AB-CDE, and AB-CD-E.By these results, the proposed method can outperform several other methods on the same dataset.

Multilayer weighted integrated self‐learning algorithm for automatic diagnosis of epileptic electroencephalogram signals

AbstractEpilepsy is a common mental disorder that affects about 70 million people worldwide. Epileptic electroencephalogram (EEG) signal, an important means to judge epileptic seizure, needs neurologists' prior knowledge to mark manually. This marking method is time‐consuming and laborious. Currently, the existing automated diagnosis methods have achieved good results on one benchmark EEG dataset, most of which can achieve accuracy of more than 0.95. However, the method has limitations on the dataset, and the accuracy of the diagnosis results on another new dataset drops sharply to nearly 0.5. Aiming at the existing EEG signal diagnosis lacks stability and generalization ability, this paper proposed a multilayer‐weighted integrated self‐learning algorithm for different classifiers. For this algorithm, weighted voting was first conducted on the the diagnostic results by different classifiers to obtain a result, which was weighted again to produce the final diagnostic results. This algorithm improves the problem that the traditional self‐learning algorithm is greatly affected by data noise, which shows a strong stability in different data sets and in clinical epileptic EEG signal data detection, so as to reduce the workload of neurologists and provide support and assistance for the diagnosis and treatment of epilepsy. The experiment result shows that the algorithm can improve the stability and reliability of EEG automatic diagnosis of epilepsy. The accuracy and AUC area of its classification in two different public data sets and clinical data can reach 0.80 to 0.95.

Identification of Epileptic Electroencephalograms Signals Using an Integrated Transfer Radius Basis Function Neural Network

As a common brain disease, epilepsy is rapidly increasing in terms of the number of patients. Long-term repeated sudden seizures seriously affect the physical and mental health of patients. Epileptic electroencephalogram (EEG) signals are an effective tool in the hands of clinicians for diagnosing epilepsy, and how to use computer technology to automatically analyze and detect epileptic EEG signals has become very meaningful. This article proposes a method for effectively identifying epileptic EEGs for further diagnosis of epilepsy. The traditional modeling method default is to train on training samples and test samples that obey the same distribution, which usually does not match the actual situation. Therefore, a transfer learning (TL) mechanism is introduced to a classical radial basis function neural network (RBFNN). Considering the limited stability of a single classifier, this article introduces an integration strategy and proposes an integrated transfer RBFNN (ITRBFNN) algorithm. Experimental results of EEG signal recognition for epilepsy show that the algorithm has better adaptability of scene transfer and stability.

A New Method Based on CEEMD Combined With Iterative Feature Reduction for Aided Diagnosis of Epileptic EEG.

In the clinical diagnosis of epileptic diseases, the intelligent diagnosis of epileptic electroencephalogram (EEG) signals has become a research focus in the field of brain diseases. In order to solve the problem of time-consuming and easily influenced by human subjective factors, artificial intelligence pattern recognition algorithm has been applied to EEG signals recognition. However, at present, the common empirical mode decomposition (EMD) signal decomposition algorithm does not consider the problem of mode aliasing. The EEG features obtained by feature extraction may be mixed with some unimportant features that affect the classification accuracy. In this paper, we proposed a new method based on complementary ensemble empirical mode decomposition (CEEMD) combined with iterative feature reduction for aided diagnosis of epileptic EEG. First of all, the evaluation indexes of decomposing and reconstructing signals by several methods were compared. The CEEMD was selected as the decomposition method of the signals. Then, the support vector machine recursive elimination (SVM-RFE) was used to reduce 9 features extracted from EEG data. The support vector classification of the gray wolf optimizer (GWO-SVC) recognition model was established for different feature subsets. By comparing the classification accuracy of training set and test set of different feature subsets, and considering the complexity of the model reflected by the number of features selected by SVM-RFE, the analysis showed that the 6 feature subsets with fewer features and higher classification accuracy could reflect the key information of epileptic EEG. The accuracy of the training set classification was 99.38% and the test set was as high as 100%. The recognition time was only 1.6551 s. Finally, in order to verify the reliability of the algorithm proposed in this paper, the proposed algorithm compared with the classification model established by the raw EEG signals and the optimization model established by other intelligent optimization algorithms. It is found that the algorithm used in this paper has higher classification accuracy and faster recognition time than other processing methods. The experimental results show that CEEMD combined with SVM-RFE is feasible for rapid and accurate recognition of EEG signals, which provides a theoretical basis for the aided diagnosis of epilepsy.

Multi‐kernel‐based random vector functional link network with decomposed features for epileptic EEG signal classification

This study proposes an improved hybrid model built with empirical mode decomposition (EMD) features combined with weighted multi-kernel random vector functional link network (WMKRVFLN) where the kernel parameters are optimised with an efficient optimisation algorithm known as water cycle algorithm (WCA) for diagnosis and classification of epileptic electroencephalogram (EEG) signals. The proposed model with optimisation is known as WCA–EMD–WMKRVFLN. The tanh and wavelet kernel functions are contributing together to the effectiveness of the proposed model. The features generated from EMD in terms of intrinsic mode functions (IMFs) are modulated to find important statistical and entropy based features and these features in a reduced form are employed as inputs to the model to classify epileptic EEG signals. The presented approach is evaluated in terms of percentage correct classification accuracy (ACC), specificity and sensitivity using two datasets and is compared with different classifiers and state-of-the-art techniques. The highest accuracies of 99.69% (five-class) and 100% (three-class) achieved using the Bonn-University dataset and 99.0% ACC (two-class) achieved using the Bern-Barcelona dataset. The achieved results report that the presented approach is a promising approach for EEG signal classification and is superior to several state-of-the-art techniques and is highly comparable to many such techniques.

Epileptic Seizure Detection in EEG Signals Using a Unified Temporal-Spectral Squeeze-and-Excitation Network.

The intelligent recognition of epileptic electro-encephalogram (EEG) signals is a valuable tool for the epileptic seizure detection. Recent deep learning models fail to fully consider both spectral and temporal domain representations simultaneously, which may lead to omitting the nonstationary or nonlinear property in epileptic EEGs and further produce a suboptimal recognition performance consequently. In this paper, an end-to-end EEG seizure detection framework is proposed by using a novel channel-embedding spectral-temporal squeeze-and-excitation network (CE-stSENet) with a maximum mean discrepancy-based information maximizing loss. Specifically, the CE-stSENet firstly integrates both multi-level spectral and multi-scale temporal analysis simultaneously. Hierarchical multi-domain representations are then captured in a unified manner with a variant of squeeze-and-excitation block. The classification net is finally implemented for epileptic EEG recognition based on features extracted in previous subnetworks. Particularly, to address the fact that the scarcity of seizure events results in finite data distribution and the severe overfitting problem in seizure detection, the CE-stSENet is coordinated with a maximum mean discrepancy-based information maximizing loss for mitigating the overfitting problem. Competitive experimental results on three EEG datasets against the state-of-the-art methods demonstrate the effectiveness of the proposed framework in recognizing epileptic EEGs, indicating its powerful capability in the automatic seizure detection.

Multiresolution approach for artifacts removal and localization of seizure onset zone in epileptic EEG signal

Epilepsy is major challenge to medical fraternity. This research article has come up with a novel method for pre-processing of Epileptic Electroencephalogram (EEG) signals for artifact removal and localizing the epileptic seizure onset zone. The presence of physiological artifacts alters the true EEG information which can considerably affect the epileptic seizure classification accuracy. Hence, it is of prime importance to eliminate these contaminations. The analysis of epileptic EEG signal requires localization of the seizure onset zone in the epileptic EEG signal. The objective of this paper is to present an approach to eliminate physiological artifacts and to localize the epileptic region. This paper suggests a hybrid model based on Multiresolutional Analysis and Adaptive Filtering [MRAF]. Initially the EEG signal is decomposed using Discrete Wavelet Transform (DWT) which effectively helps to localize the epileptic region. Multiresolutional soft thresholding is applied to these decomposed wavelet components to remove the abrupt variations. Further, adaptive filtering is applied to remove the low frequency components which represents physiological artifacts. It is observed that the MRAF method effectively eliminate physiological artifacts and localizes the epileptic seizure zone present in the seizure EEG information. The accuracy of the proposed MRAF model is found to be 86.66% with a precision of 88.88%, since it is able to retain most of the seizure signal present in the tested datasets.

Electroencephalographic biomarkers of epilepsy development in patients with acute brain injury: a matched, parallel cohort study.

ObjectiveThis study was designed to investigate if highly epileptic electroencephalogram (EEG) findings in patients with acute brain injury increase the long‐term risk of epilepsy development.MethodsAdults patients, lacking epilepsy history, with electrographic seizures or lateralized periodic discharges (LPDs) (cases) were identified and matched based on age, mental status, and etiology with the ones lacking any epileptiform activity (controls) on continuous EEG (cEEG) during hospitalization. The primary outcome of clinical seizures after hospital discharge and their antiepileptic drug (AED) status was determined using a telephonic interview. Logistic regression models using generalized estimating equations to account for the matched nature of the data were performed.ResultsA total of 70 cases [16 (22.9%) “LPDs only,” 34 (48.6%) “electrographic seizure only,” and 20 (28.6%) “both”] and controls were enrolled. A total of 22 (31.4%) cases developed epilepsy after a mean follow‐up duration of 20.6 ± 5.0 months compared to three (4.3%) controls. After adjusting for cEEG indication and follow‐up duration, the odds of cases developing epilepsy were almost 15 times higher compared to the controls (OR = 14.8, 95% CI = 2.4–92.3, P = 0.004). This elevated risk was despite a 10 times higher likelihood of cases to be taking AEDs at the last follow‐up (OR = 10.34, 95% CI = 3.7–29, P < 0.001).InterpretationHighly epileptic EEG findings in patients with acute brain injury may serve as prognostic biomarkers of epilepsy development. Although prospective studies are required to confirm our findings, it seems that with epilepsy developing in almost one‐third cases in less than 2‐year follow‐up period, such patients may potentially be ideal candidates for epilepsy prevention clinical trials.

Analysis of epileptic seizure detection method based on improved genetic algorithm optimization back propagation neural network

In order to improve the accuracy and efficiency of automatic seizure detection, the paper proposes a method based on improved genetic algorithm optimization back propagation (IGA-BP) neural network for epilepsy diagnosis, and uses the method to achieve detection of clinical epilepsy rapidly and effectively. Firstly, the method extracted the linear and nonlinear features of the epileptic electroencephalogram (EEG) signals and used a Gaussian mixture model (GMM) to perform cluster analysis on EEG features. Next, expectation maximization (EM) algorithm was used to estimate GMM parameters to calculate the optimal parameters for the selection operator of genetic algorithm (GA). The initial weights and thresholds of the BP neural network were obtained through using the improved genetic algorithm. Finally, the optimized BP neural network is used for the classification of the epileptic EEG signals to detect the epileptic seizure automatically. Compared with the traditional genetic algorithm optimization back propagation (GA-BP), the IGA-BP neural network can improve the population convergence rate and reduce the classification error. In the process of automatic detection of epilepsy, the method improves the detection accuracy in the automatic detection of epilepsy disorders and reduced inspection time. It has important application value in the clinical diagnosis and treatment of epilepsy.

Epileptic EEG signal classification using optimum allocation based power spectral density estimation

This study proposes a novel approach blending optimum allocation (OA) technique and spectral density estimation to analyse and classify epileptic electroencephalogram (EEG) signals. This study employs the OA to determine representative sample points from the original EEG data and then applies periodogram (PD), autoregressive (AR), and the mixture of PD and AR to extract the discriminative features from each OA sample group. The obtained feature sets are evaluated by three popular machine learning methods: support vector machine (SVM), quadratic discriminant analysis (QDA), and k -nearest neighbour (k-NN). Several output coding approaches of the SVM classifier are tested for selecting the best feature sets. This scheme was implemented on a benchmark epileptic EEG database for evaluation and also compared with existing methods. The experimental results show that the OA_AR feature set yields better performances by the SVM with an overall accuracy of 100%, and outperforms the state-of-the-art works with a 14.1% improvement. Thus, the findings of this study prove that the proposed OA-based AR scheme has significant potential to extract features from EEG signals. The proposed method will assist experts to automatically analyse a large volume of EEG data and benefit epilepsy research.

A Classification Method for Epileptic Electroencephalogram Based on Wavelet Multi-scale Analysis and Particle Swarm Optimization Algorithm

The automatic classification of epileptic electroencephalogram (EEG) is important for the diagnosis and treatment of epilepsy. In this paper, an epileptic EEG classification method based on wavelet multi-scale analysis and particle swarm optimization is proposed. Firstly, the multi-scale is carried out to the original EEG to extract its sub-bands of different frequency. Secondly, the Hurst exponent and the sample entropy are used to extract the EEG signals and its sub-bands. Finally, the particle swarm optimization (PSO) algorithm is used to optimize the parameters of the extreme learning machine (ELM), and the obtained eigenvector is put to PSO-ELM to realize the purpose of classification of epileptic EEG. The proposed method in this paper achieved 99.7% classification accuracy for the discrimination between epileptic ictal and interictal EEG, which is superior to those methods in other studies.

Chaos feature study in fractional Fourier domain for preictal prediction of epileptic seizure

Epileptic seizure prediction is limited by the unstable performance of suboptimal models. Studies of new methods for reliable preictal prediction have significant impact on the control, early care and online treatment of epileptic seizure. The traditional chaos measure does not effectively identify multiple states of epileptic electroencephalogram (EEG). A novel method was adopted to capture subtle chaotic dynamics for epileptic signals in fractional Fourier transform domain. Algorithm of the largest Lyapunov exponent was modified to adapt the transformed series by using an energy measure to determine appropriate fractional order. The performance of our proposed method was evaluated with an automatic model of preictal prediction using artificial neural networks as classifier. The results showed that the new model yielded higher accuracy in identifying the preictal state compared to the original largest Lyapunov exponent. Experimental results with noisy scalp epileptic EEGs also demonstrated the potential and robustness of our approach to discriminate preictal from interictal and ictal states, and it provided a novel methodology for reliable preictal prediction of epileptic seizure.

Recognition of Epileptic EEG Signals Using a Novel Multiview TSK Fuzzy System

Recognition of epileptic electroencephalogram (EEG) signals using machine learning techniques is becoming popular. In general, the construction of intelligent epileptic EEG recognition system involves two steps. First, an appropriate feature extraction method is applied to obtain representative features from the original raw EEG signals. Second, an effective intelligent model is trained based on the extracted features. However, there exist two major challenges in the process: 1) it is nontrivial to determine the appropriate feature extraction method to be used; 2) although many classical machine learning methods have been used for epileptic EEG recognition, most of them are “black box” approaches and more interpretable methods are desirable. To address these two challenges, a new epileptic EEG recognition method based on a multiview learning framework and fuzzy system modeling is proposed. First, multiview EEG data are generated by employing different feature extraction methods to obtain the features from different views of the signals. Second, the classical Takagi-Sugeno-Kang fuzzy system (TSK-FS) is introduced as an easy-to-interpret recognition model to develop a multiview TSK-FS method, called MV-TSK-FS, to identify epileptic EEG signals. For the proposed MV-TSK-FS, the importance of each view, i.e., the importance of each feature extraction method, can be evaluated according to the weighting of each view, and consequently the final decision can be made based on the weighted outputs of different views. Experimental results indicate that the MV-TSK-FS is a promising method when compared with the state-of-the-art algorithms.

The effects of carbamazepine in the intrahippocampal kainate model of temporal lobe epilepsy depend on seizure definition and mouse strain.

SummaryObjectiveMesial temporal lobe epilepsy (TLE) with hippocampal sclerosis is a predominant form of acquired epilepsy, characterized by recurrent simple and complex partial seizures that are often resistant to treatment. Mice developing spontaneous recurrent nonconvulsive and convulsive seizures after intrahippocampal injection of the excitotoxic glutamate agonist kainate are thought to represent a valuable model of mesial TLE. Epileptic electroencephalogram (EEG) activity recorded in this model from the kainate focus in the ipsilateral hippocampus is resistant to antiseizure drugs such as carbamazepine (CBZ). We compared the efficacy of CBZ in this model in two different mouse strains (FVB/N and NMRI). Furthermore, we evaluated whether changes in the definition of electrographic seizures affect the antiseizure efficacy of CBZ.MethodsAs in previous studies, two types of epileptic EEG activity were defined: high‐voltage sharp waves (HVSWs) and hippocampal paroxysmal discharges (HPDs). The characteristics of these paroxysmal EEG events in epileptic mice were compared with EEG criteria for nonconvulsive seizures in patients. For HVSWs, different spike frequencies, interevent intervals, and amplitudes were used as inclusion and exclusion criteria. In addition to CBZ, some experiments were performed with diazepam (DZP) and phenobarbital (PB).ResultsFemale epileptic FVB/N mice predominantly exhibited frequent HVSWs, but only infrequent HPDs or secondarily generalized convulsive seizures. Slight changes in HVSW definition determined whether they were resistant or responsive to CBZ. Male NMRI mice exhibited both HVSWs and HPDs. HVSWs were more resistant than HPDs to suppression by CBZ. Both types of epileptic EEG activity were rapidly suppressed by DZP and PB.SignificanceThe data demonstrate that focal electrographic seizures in the intrahippocampal kainate mouse model are less resistant than previously thought. Both mouse strain and the criteria chosen for definition of EEG seizures determine whether such seizures are drug‐resistant or ‐responsive.

Epileptic EEG visualization and sonification based on linear discriminate analysis.

In this paper, we first presents a high accuracy epileptic electroencephalogram (EEG) classification algorithm. EEG data of epilepsy patients are preprocessed, segmented, and decomposed to intrinsic mode functions, from which features are extracted. Two classifiers are trained based on linear discriminant analysis (LDA) to classify EEG data into three types, i.e., normal, spike, and seizure. We further in-depth investigate the changes of the decision values in LDA on continuous EEG data. An epileptic EEG visualization and sonification algorithm is proposed to provide both temporal and spatial information of spike and seizure of epilepsy patients. In the experiment, EEG data of six subjects (two normal and four seizure patients) are included. The experiment result shows the proposed epileptic EEG classification algorithm achieves high accuracy. As well, the visualization and sonification algorithm exhibits a great help in nursing seizure patients and localizing the area of seizures.

Multiscale permutation entropy analysis of electroencephalogram

We carried out a detailed analysis and a comparison between normal and epileptic electroencephalogram (EEG) based on multiscale permutation entropy. The relationship between multiscale permutation entropy values of EEG and age, and the effect of scale factor on multiscale permutation entropy value were also discussed. By analyzing normal and epileptic EEG based on multiscale permutation entropy, we found that, at the same age, multiscale permutation entropy value of the normal group’s EEG is higher than that of the epileptic group by an average of 0.19, about 7.9%. In addition, for people of age 3 to 35, their multiscale permutation entropies are clearly maximum. When scale factor is smaller than 15, the value of their entropy would reduce no matter whether the age increases or decreases. The results indicate that multiscale permutation entropy can distinguish between normal and epileptic EEG and reflect the general process of human brain development.

Optimal Classification of Epileptic EEG Signals Using Neural Networks and Harmony Search Methods

In this paper, the Harmony Search (HS)-aided BP neural networks are used for the classification of the epileptic electroencephalogram (EEG) signals. It is well known that the gradient descent-based learning method can result in local optima in the training of BP neural networks, which may significantly affect their approximation performances. Three HS methods, the original version and two new variations recently proposed by the authors of the present paper, are applied here to optimize the weights in the BP neural networks for the classification of the epileptic EEG signals. Simulations have demonstrated that the classification accuracy of the BP neural networks can be remarkably improved by the HS method-based training.

Model-Based Spike Detection of Epileptic EEG Data

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.