Prediction of epilepsy seizure from multi-channel electroencephalogram by effective connectivity analysis using Granger causality and directed transfer function methods

Identification of epileptic networks with graph convolutional network incorporating oscillatory activities and evoked synaptic responses

Stereoelectroencephalography (SEEG) offers unique neural data from in-depth brain structures with fine temporal resolutions to better investigate the origin of epileptic brain activities. Although oscillatory patterns from different frequency bands and functional connectivity computed from the SEEG datasets are employed to study the epileptic zones, direct electrical stimulation-evoked electrophysiological recordings of synaptic responses, namely cortical-cortical evoked potentials (CCEPs), from the same SEEG electrodes are not explored for the localization of epileptic zones. Here we proposed a two-stream model with unsupervised learning and graph convolutional network tailored to the SEEG and CCEP datasets in individual patients to perform localization of epileptic zones. We compared our localization results with the clinically marked electrode sites determined for surgical resections. Our model had good classification capability when compared to other state-of-the-art methods. Furthermore, based on our prediction results we performed group-level brain-area mapping analysis for temporal, frontal and parietal epilepsy patients and found that epileptic and non-epileptic brain networks were distinct in patients with different types of focal epilepsy. Our unsupervised data-driven model provides personalized localization analysis for the epileptic zones. The epileptic and non-epileptic brain areas disclosed by the prediction model provide novel insights into the network-level pathological characteristics of epilepsy.

Classification of the Epileptic Seizure Onset Zone Based on Partial Annotation

Epilepsy is a chronic disorder caused by excessive electrical discharges. Currently, clinical experts identify the seizure onset zone (SOZ) channel through visual judgment based on long-time intracranial electroencephalogram (iEEG), which is a very time-consuming, difficult and experience-based task. Therefore, there is a need for high-accuracy diagnostic aids to reduce the workload of clinical experts. In this article, we propose a method in which, the iEEG is split into the 20-s segment and for each patient, we ask clinical experts to label a part of the data, which is used to train a model and classify the remaining iEEG data. In recent years, machine learning methods have been successfully applied to solve some medical problems. Filtering, entropy and short-time Fourier transform (STFT) are used for extracting features. We compare them to wavelet transform (WT), empirical mode decomposition (EMD) and other traditional methods with the aim of obtaining the best possible discriminating features. Finally, we look for their medical interpretation, which is important for clinical experts. We achieve high-performance results for SOZ and non-SOZ data classification by using the labeled iEEG data and support vector machine (SVM), fully connected neural network (FCNN) and convolutional neural network (CNN) as classification models. In addition, we introduce the positive unlabeled (PU) learning to further reduce the workload of clinical experts. By using PU learning, we can learn a binary classifier with a small amount of labeled data and a large amount of unlabeled data. This can greatly reduce the amount and difficulty of annotation work by clinical experts. All together, we show that using 105 minutes of labeled data we achieve a classification result of 91.46% on average for multiple patients.

Closed-loop seizure modulation via extreme learning machine based extended state observer

Neuromodulation is a promising way in clinical treatment of epilepsy, but the existing methods cannot adjust stimulations according to patients' real-time reactions. Therefore, it is necessary to acquire a systematic and a scientific regulation method based on patients' real-time reactions. The linear active disturbance rejection control can adapt to complex epileptic dynamics and improve the epilepsy regulation, even if little model information is available, and various uncertainties and external disturbances exist. However, a linear extended state observer estimates the time-varying total disturbance with a steady-state error. To improve regulation, it is crucial to estimate the total disturbance in a more accurate manner. An extreme learning machine is capable of approximating any nonlinear function. Its initial parameter generation is more convenient, adjustable parameters are fewer, and learning speed is faster. Thus, a nonlinear time-varying function can be estimated more timely and accurately. Then, an extreme learning machine based extended state observer is proposed to get a more satisfactory total disturbance estimation and more desired closed-loop regulation. The convergence of the extreme learning machine based extended state observer is verified and the stability of the closed-loop system is analyzed. Numerical results show that the proposed extended state observer is much better than a linear extended state observer in estimating the total disturbance. It guarantees a more satisfied closed-loop neuromodulation.

Optimized adaptive neuro-fuzzy inference system based on hybrid grey wolf-bat algorithm for schizophrenia recognition from EEG signals

Schizophrenia is a chronic mental disorder that impairs a person's thinking capacity, feelings and emotions, behavioural traits, etc., Emotional distortions, delusions, hallucinations, and incoherent speech are all some of the symptoms of schizophrenia, and cause disruption of routine activities. Computer-assisted diagnosis of schizophrenia is significantly needed to give its patients a higher quality of life. Hence, an improved adaptive neuro-fuzzy inference system based on the Hybrid Grey Wolf-Bat Algorithm for accurate prediction of schizophrenia from multi-channel EEG signals is presented in this study. The EEG signals are pre-processed using a Butterworth band pass filter and wICA initially, from which statistical, time-domain, frequency-domain, and spectral features are extracted. Discriminating features are selected using the ReliefF algorithm and are then forwarded to ANFIS for classification into either schizophrenic or normal. ANFIS is optimized by the Hybrid Grey Wolf-Bat Algorithm (HWBO) for better efficiency. The method is experimented on two separate EEG datasets-1 and 2, demonstrating an accuracy of 99.54% and 99.35%, respectively, with appreciable F1-score and MCC. Further experiments reveal the efficiency of the Hybrid Wolf-Bat algorithm in optimizing the ANFIS parameters when compared with traditional ANFIS model and other proven algorithms like genetic algorithm-ANFIS, particle optimization-ANFIS, crow search optimization algorithm-ANFIS and ant colony optimization algorithm-ANFIS, showing high R2 value and low RSME value. To provide a bias free classification, tenfold cross validation is performed which produced an accuracy of 97.8% and 98.5% on the two datasets respectively. Experimental outcomes demonstrate the superiority of the Hybrid Grey Wolf-Bat Algorithm over the similar techniques in predicting schizophrenia.

Fusion Graph Representation of EEG for Emotion Recognition

Various relations existing in Electroencephalogram (EEG) data are significant for EEG feature representation. Thus, studies on the graph-based method focus on extracting relevancy between EEG channels. The shortcoming of existing graph studies is that they only consider a single relationship of EEG electrodes, which results an incomprehensive representation of EEG data and relatively low accuracy of emotion recognition. In this paper, we propose a fusion graph convolutional network (FGCN) to extract various relations existing in EEG data and fuse these extracted relations to represent EEG data more comprehensively for emotion recognition. First, the FGCN mines brain connection features on topology, causality, and function. Then, we propose a local fusion strategy to fuse these three graphs to fully utilize the valuable channels with strong topological, causal, and functional relations. Finally, the graph convolutional neural network is adopted to represent EEG data for emotion recognition better. Experiments on SEED and SEED-IV demonstrate that fusing different relation graphs are effective for improving the ability in emotion recognition. Furthermore, the emotion recognition accuracy of 3-class and 4-class is higher than that of other state-of-the-art methods.

[Dynamic analysis of epileptic causal brain networks based on directional transfer function]

Epilepsy is a neurological disease with disordered brain network connectivity. It is important to analyze the brain network mechanism of epileptic seizure from the perspective of directed functional connectivity. In this paper, causal brain networks were constructed for different sub-bands of epileptic electroencephalogram (EEG) signals in interictal, preictal and ictal phases by directional transfer function method, and the information transmission pathway and dynamic change process of brain network under different conditions were analyzed. Finally, the dynamic changes of characteristic attributes of brain networks with different rhythms were analyzed. The results show that the topology of brain network changes from stochastic network to rule network during the three stage and the node connections of the whole brain network show a trend of gradual decline. The number of pathway connections between internal nodes of frontal, temporal and occipital regions increase. There are a lot of hub nodes with information outflow in the lesion region. The global efficiency in ictal stage of α, β and γ waves are significantly higher than in the interictal and the preictal stage. The clustering coefficients in preictal stage are higher than in the ictal stage and the clustering coefficients in ictal stage are higher than in the interictal stage. The clustering coefficients of frontal, temporal and parietal lobes are significantly increased. The results of this study indicate that the topological structure and characteristic properties of epileptic causal brain network can reflect the dynamic process of epileptic seizures. In the future, this study has important research value in the localization of epileptic focus and prediction of epileptic seizure.

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

The recurrent and unpredictable nature of seizures can lead to unintentional injuries and even death. The rapid development of electroencephalogram (EEG) and Artificial Intelligence (AI) technologies has made it possible to predict seizures in real-time through brain-machine interfaces (BCI), allowing advanced intervention. To date, there is still much room for improvement in predictive seizure models constructed by EEG using machine learning (ML) and deep learning (DL). But, the most critical issue is how to improve the performance and generalization of the model, which involves some confusing conceptual and methodological issues. This review focuses on analyzing several factors affecting the performance of seizure prediction models, focusing on the aspects of post-processing, seizure occurrence period (SOP), seizure prediction horizon (SPH), and algorithms. Furthermore, this study presents some new directions and suggestions for building high-performance prediction models in the future. We aimed to clarify the concept for future research in related fields and improve the performance of prediction models to provide a theoretical basis for future applications of wearable seizure detection devices.

Inferring the dynamical effects of stroke lesions through whole-brain modeling

Understanding the effect of focal lesions (stroke) on brain structure-function traditionally relies on behavioral analyses and correlation with neuroimaging data. Here we use structural disconnection maps from individual lesions to derive a causal mechanistic generative whole-brain model able to explain both functional connectivity alterations and behavioral deficits induced by stroke. As compared to other models that use only the local lesion information, the similarity to the empirical fMRI connectivity increases when the widespread structural disconnection information is considered. The presented model classifies behavioral impairment severity with higher accuracy than other types of information (e.g.: functional connectivity). We assessed topological measures that characterize the functional effects of damage. With the obtained results, we were able to understand how network dynamics change emerge, in a nontrivial way, after a stroke injury of the underlying complex brain system. This type of modeling, including structural disconnection information, helps to deepen our understanding of the underlying mechanisms of stroke lesions.

NLGC: Network Localized Granger Causality with Application to MEG Directional Functional Connectivity Analysis

Identifying the directed connectivity that underlie networked activity between different cortical areas is critical for understanding the neural mechanisms behind sensory processing. Granger causality (GC) is widely used for this purpose in functional magnetic resonance imaging analysis, but there the temporal resolution is low, making it difficult to capture the millisecond-scale interactions underlying sensory processing. Magnetoencephalography (MEG) has millisecond resolution, but only provides low-dimensional sensor-level linear mixtures of neural sources, which makes GC inference challenging. Conventional methods proceed in two stages: First, cortical sources are estimated from MEG using a source localization technique, followed by GC inference among the estimated sources. However, the spatiotemporal biases in estimating sources propagate into the subsequent GC analysis stage, may result in both false alarms and missing true GC links. Here, we introduce the Network Localized Granger Causality (NLGC) inference paradigm, which models the source dynamics as latent sparse multivariate autoregressive processes and estimates their parameters directly from the MEG measurements, integrated with source localization, and employs the resulting parameter estimates to produce a precise statistical characterization of the detected GC links. We offer several theoretical and algorithmic innovations within NLGC and further examine its utility via comprehensive simulations and application to MEG data from an auditory task involving tone processing from both younger and older participants. Our simulation studies reveal that NLGC is markedly robust with respect to model mismatch, network size, and low signal-to-noise ratio, whereas the conventional two-stage methods result in high false alarms and mis-detections. We also demonstrate the advantages of NLGC in revealing the cortical network-level characterization of neural activity during tone processing and resting state by delineating task- and age-related connectivity changes.

Deep-layer motif method for estimating information flow between EEG signals

Accurate identification for the information flow between epileptic seizure signals is the key to construct the directional epileptic brain network which can be used to localize epileptic focus. In this paper, our concern is on how to improve the direction identification of information flow and also investigate how it can be cut off or weakened. In view of this, we propose the deep-layer motif method. Based on the directional index (DI) estimation using permutation conditional mutual information, the effectiveness of the proposed deep-layer motif method is numerically assessed with the coupled mass neural model. Furthermore, we investigate the robustness of this method in considering the interference of autaptic coupling, time delay and short-term plasticity. Results show that compared to the simple 1-layer motif method, the 2nd- and 3rd-layer motif methods have the dominant enhancement effects for the direction identification. In particular, deep-layer motif method possesses good anti-jamming performance and good robustness in calculating DI. In addition, we investigate the effect of deep brain stimulation (DBS) on the information flow. It is found that this deep-layer motif method is still superior to the single-layer motif method in direction identification and is robust to weak DBS. However, the high-frequency strong DBS can effectively decrease the DI suggesting the weakened information flow. These results may give new insights into the seizure detection and control.

Coupling feature extraction method of resting state EEG Signals from amnestic mild cognitive impairment with type 2 diabetes mellitus based on weight permutation conditional mutual information

This study aimed to find a good coupling feature extraction method to effectively analyze resting state EEG signals (rsEEG) of amnestic mild cognitive impairment(aMCI) with type 2 diabetes mellitus(T2DM) and normal control (NC) with T2DM. A method of EEG signal coupling feature extraction based on weight permutation conditional mutual information (WPCMI) was proposed in this research. With the WPCMI method, coupling feature strength of two time series in Alpha1, Alpha2, Beta1, Beta2 and Gamma bands for aMCI with T2DM and NC with T2DM could be extracted respectively. Then selected three frequency bands coupling feature matrix with the help of multi-spectral image transformation method to map it as spectral image characteristics. And finally classified these characteristics through the convolution neural network method(CNN). For aMCI with T2DM and NC with T2DM, the highest classification accuracy of 96%, 95%, 95% could be achieved respectively in the combination of three frequency bands (Alpha1, Alpha2, Gamma), (Beta1, Beta2 and Gamma) and (Alpha2, Beta1, Beta2). This WPCMI method highlighted the coupling dynamic characteristics of EEG signals, and its classification performance was better than all previous methods in aMCI with T2DM diagnosis field. WPCMI method could be used as an effective biomarker to distinguish EEG signals of aMCI with T2DM and NC with T2DM. The coupling feature extraction method used in this paper provided a new perspective for the EEG analysis of aMCI with T2DM.

Complex networks and deep learning for EEG signal analysis

Electroencephalogram (EEG) signals acquired from brain can provide an effective representation of the human's physiological and pathological states. Up to now, much work has been conducted to study and analyze the EEG signals, aiming at spying the current states or the evolution characteristics of the complex brain system. Considering the complex interactions between different structural and functional brain regions, brain network has received a lot of attention and has made great progress in brain mechanism research. In addition, characterized by autonomous, multi-layer and diversified feature extraction, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, including brain state research. Both of them show strong ability in EEG signal analysis, but the combination of these two theories to solve the difficult classification problems based on EEG signals is still in its infancy. We here review the application of these two theories in EEG signal research, mainly involving brain-computer interface, neurological disorders and cognitive analysis. Furthermore, we also develop a framework combining recurrence plots and convolutional neural network to achieve fatigue driving recognition. The results demonstrate that complex networks and deep learning can effectively implement functional complementarity for better feature extraction and classification, especially in EEG signal analysis.

Sharp decrease in the Laplacian matrix rank of phase-space graphs: a potential biomarker in epilepsy

In this paper, phase space reconstruction from stereo-electroencephalography data of ten patients with focal epilepsy forms a series of graphs. Those obtained graphs reflect the transition characteristics of brain dynamical system from pre-seizure to seizure of epilepsy. Interestingly, it is found that the rank of Laplacian matrix of these graphs has a sharp decrease when a seizure is close to happen, which thus might be viewed as a new potential biomarker in epilepsy. In addition, the reliability of this method is numerically verified with a coupled mass neural model. In particular, our simulation suggests that this potential biomarker can play the roles of predictive effect or delayed awareness, depending on the bias current of the Gaussian noise. These results may give new insights into the seizure detection.

A novel quality prediction model for component based software system using ACO-NM optimized extreme learning machine

Component-based software engineering is currently a development strategy used to improve complex embedded systems. The engineers have to deal with a large number of quality requirements (e.g. safety, security, availability, reliability, maintainability, portability, performance, and temporal correctness requirements), hence the development of complex embedded systems is becoming a challenging task. Enhancement of the quality prediction in component-based software engineering systems using soft computing techniques is the foremost intention of the research. Therefore, this paper proposes an extreme learning machine (ELM) classifier with the ant colony optimization algorithm and Nelder-Mead (ACO-NM) soft computing approach for component quality prediction. To promote efficient software systems and the ability of the software to work under several computer configurations maintainability, independence, and portability are taken as three core software components metrics for measuring the quality prediction. The ELM uses AC-NM for updating its weight to transform the quality constraints into objective functions for providing a global optimum quality prediction. The experimental results have shown that the proposed work gives an improved performance in terms of Sensitivity, Precision, Specificity, Accuracy, Mathews correlation coefficient, false positive rate, negative predictive value, false discovery rate, and rate of convergence.

Localizing confined epileptic foci in patients with an unclear focus or presumed multifocality using a component-based EEG-fMRI method

Precise localization of epileptic foci is an unavoidable prerequisite in epilepsy surgery. Simultaneous EEG-fMRI recording has recently created new horizons to locate foci in patients with epilepsy and, in comparison with single-modality methods, has yielded more promising results although it is still subject to limitations such as lack of access to information between interictal events. This study assesses its potential added value in the presurgical evaluation of patients with complex source localization. Adult candidates considered ineligible for surgery on account of an unclear focus and/or presumed multifocality on the basis of EEG underwent EEG-fMRI. Adopting a component-based approach, this study attempts to identify the neural behavior of the epileptic generators and detect the components-of-interest which will later be used as input in the GLM model, substituting the classical linear regressor. Twenty-eight sets interictal epileptiform discharges (IED) from nine patients were analyzed. In eight patients, at least one BOLD response was significant, positive and topographically related to the IEDs. These patients were rejected for surgery because of an unclear focus in four, presumed multifocality in three, and a combination of the two conditions in two. Component-based EEG-fMRI improved localization in five out of six patients with unclear foci. In patients with presumed multifocality, component-based EEG-fMRI advocated one of the foci in five patients and confirmed multifocality in one of the patients. In seven patients, component-based EEG-fMRI opened new prospects for surgery and in two of these patients, intracranial EEG supported the EEG-fMRI results. In these complex cases, component-based EEG-fMRI either improved source localization or corroborated a negative decision regarding surgical candidacy. As supported by the statistical findings, the developed EEG-fMRI method leads to a more realistic estimation of localization compared to the conventional EEG-fMRI approach, making it a tool of high value in pre-surgical evaluation of patients with refractory epilepsy. To ensure proper implementation, we have included guidelines for the application of component-based EEG-fMRI in clinical practice.

Functional and effective connectivity based features of EEG signals for object recognition

Classifying different object categories is one of the most important aims of brain-computer interface researches. Recently, interactions between brain regions were studied using different methods, such as functional and effective connectivity techniques. Functional and effective connectivity techniques are applied to estimate human brain areas connectivity. The main purpose of this study is to compare classification accuracy of the most advanced functional and effective methods in order to classify 12 basic object categories using Electroencephalography (EEG) signals. In this paper, 19 channels EEG signals were collected from 10 healthy subjects; when they were visiting color images and instructed to select the target images among others. Correlation, magnitude square coherence, wavelet coherence (WC), phase synchronization and mutual information were applied to estimate functional cortical connectivity. On the other hand, directed transfer function, partial directed coherence, generalized partial directed coherence (GPDC) were used to obtain effective cortical connectivity. After feature extraction, the scalar feature selection methods including T-test and one-sided-anova were applied to rank and select the most informative features. The selected features were classified by a one-against-one support vector machine classifier. The results indicated that the use of different techniques led to different classifying accuracy and brain lobes analysis. WC and GPDC are the most accurate methods with performances of 80.15% and 64.43%, respectively.

Frontal-temporal functional connectivity of EEG signal by standardized permutation mutual information during anesthesia

Quantifying brain dynamics during anesthesia is an important challenge for understanding the neurophysiological mechanisms of anesthetic drug effect. Several single channel Electroencephalogram (EEG) indices have been proposed for monitoring anesthetic drug effect. The most commonly used single channel commercial index is the Bispectral index (BIS). However, this monitor has shown some drawbacks. In this study, a nonlinear functional connectivity measure named Standardized Permutation Mutual Information (SPMI) is proposed to describe communication between two-channel EEG signals at frontal and temporal brain regions during a controlled propofol-induced anesthesia and recovery design from eight subjects. The SPMI index has higher correlation with estimated propofol effect-site concentration and has better ability to distinguish three anesthetic states of patient than the other functional connectivity indexes (cross-correlation, coherence, phase analysis) and also the BIS index. Moreover, the SPMI index has a faster reaction to the effect of drug concentration, less variability at the consciousness state and better robustness to noise than BIS.