Scalp EEG Data Research Articles

Classification of EEG signals: An interpretable approach using functional data analysis

Electroencephalography (EEG) is a noninvasive method to record electrical activity of the brain. The EEG data is continuous flow of voltages, in this paper, we consider them as functional data, and propose a three-stage algorithm based on functional data analysis, with the advantage of interpretability. Specifically, the time and frequency information are extracted by wavelet transform in the first stage. Then, functional testing is utilized to select EEG channels and frequencies that show significant differences for different human behaviors. In the third stage, we propose to use penalized multiple functional logistic regression to interpretably classify human behaviors. With simulation and a scalp EEG data as validation set, we show that the proposed three-stage algorithm provides an interpretable classification of the scalp EEG signals.

Channel based epilepsy seizure type detection from electroencephalography (EEG) signals with machine learning techniques

Epileptic seizures result from disturbances in the electrical activity of the brain, classified as focal, generalized, or unknown. Failure to correctly classify epileptic seizures may result in inappropriate treatment and continuation of seizures. Therefore, automatic detection of generalized, focal, and other epileptic seizures from EEG signals is important. In this research article, Focal-Generalized classification method is proposed that compares traditional classification algorithms and deep learning methods. Two different classifications: four-class (Case (I) Complex Partial Seizure (CPSZ) (C4-T4 Onset)-CPSZ (FP2-F8 Onset)-CPSZ (T5-O1 Onset)- Absence Seizure (ABSZ)) and two-class (Case (II) CPSZ-ABSZ) problems are considered. This study includes preprocessing of scalp Electroencephalogram (EEG) data, feature extraction with discrete wavelet method, feature selection using Correlation-based Feature Selection (CFS) method, and classification of data with classifier algorithms (K-Nearest Neighbors (Knn), Support Vector Machine (SVM), Random Forest (RF) and Long Short-Term Memory (LSTM). The proposed method was applied on 23 subjects in the Temple University Hospital (TUH) scalp EEG data set, and a classification success rate of 95,92% for case (I) and 98,08% for case (II) was successfully achieved with deep learning architecture LSTM.

Combined Yoga and Transcranial Direct Current Stimulation Increase Functional Connectivity and Synchronization in the Frontal Areas.

Transcranial direct current stimulation (tDCS) is a non-invasive neuro-stimulation technique that can modulate cortical excitability. Similarly, yoga is shown to affect the brain's neural activity and networks. Here, we aimed to investigate the effect of combined yoga and tDCS on brain oscillations and networks using resting-state electroencephalography recordings. In a randomized, cross-over, double-blind design, twenty-two healthy subjects participated in a yoga/active tDCS session (2mA; 20min; anode-F3, cathode F4) or yoga/sham tDCS on 2 separate days. Resting-state EEG data were collected before and after each intervention. Power spectral density (PSD) and functional connectivity, measured by a synchronization measure, phase-locking value, were computed for each condition. There were no significant differences in PSD values among the two interventions. The network-based statistic method was employed for detecting functional connectivity differences between yoga/active and yoga/sham tDCS interventions. Results show that the addition of active tDCS to yoga is associated with increased functional connectivity of the scalp and source EEG data in the frontal area. The changes were widespread, intra-hemispheric, and inter-hemispheric connections, which were mainly between the frontal area to other regions. At the source level, most of the connectivity changes were found in the fronto-parietal network. These findings suggest that combining yoga with tDCS might lead to brain network changes related to the executive and attentional functions.

Stable decoding of working memory load through frequency bands

ABSTRACT Numerous studies have shown that working memory modulates every frequency band’s power in the human brain. Yet, the question of how the highly distributed working memory adapts to external demands remains unresolved. Here, we explored frequency band modulations underlying working memory load, taking executive control under account. We hypothesized that synchronizations underlying various cognitive functions may be sequenced in time to avoid interference and that transient modulation of decoding accuracy of task difficulty would vary with increasing difficulty. We recorded whole scalp EEG data from 12 healthy participants, while they performed a visuo-spatial n-back task with three conditions of increasing difficulty, after an initial learning phase. We analyzed evoked spectral perturbations and time-resolved decoding of individual synchronization. Surprisingly, our results provide evidence for persistent decoding above the level-of-chance (83.17% AUC) for combined frequency bands. In fact, the decoding accuracy was higher for the combined than for isolated frequency bands (AUC from 65.93% to 74.30%). However, in line with our hypothesis, frequency band clusters transiently emerged in parieto-occipital regions within two separate time windows for alpha-/beta-band (relative synchronization from approximately 200 to 600 ms) and for the delta-/theta-band (relative desynchronization from approximately 600 to 1000 ms). Overall, these findings highlight concurrent sustained and transient measurable features of working memory load. This could reflect the emergence of stability within and between functional networks of the complex working memory system. In turn, this process allows energy savings to cope with external demands.

A new method of localizing brain activity using the scalp EEG data

We propose a spatial localization method for scalp electroencephalography (EEG). The technique allows reliable and unambiguous identification of the activity for any intracerebral source by its spatial coordinates. Our "virtually implanted electrode" is based on the dynamics and correlation analysis of signals in the EEG leads with the addition of artificially generated data. The generated data helps us accurately model the electrical potential distribution between the studied source and the scalp electrodes. Each modeled intracerebral source is analyzed independently, so the proposed method does not require an estimate of the possible number of sources. The method produces output values that can be interpreted as the "local field" elec-trical activity for the implanted electrode in the corresponding brain point. The signal cleaning procedure makes it possible to exclude the influence from neighboring regions and detect a given brain region's isolated electrical activity. For verification, the method was applied in the empathy study on a sample of 16 people. We compared the background EEG of calm wakefulness with the EEG of empathic behavior for the 33 preselected brain regions.

ПСИХОФИЗИОЛОГИЧЕСКИЕ МЕХАНИЗМЫ ВНУТРЕННЕГО ПРОГОВАРИВАНИЯ ФОНЕМ

Relevance. Th e problem of identifying the cerebral mechanisms of internal speech (spoken words or even individual sounds — phonemes) based on the electrical activity of the brain is relevant and signifi cant for a number of practical applications, in particular for improving the construction of brain-computer interfaces. Target. Electroencephalographic research is aimed at identifying the cerebral mechanisms of internal speech, taking into account the modality of its initialization. Methodology. In a study on 25 subjects, a 19-channel EEG was recorded in the process of performing three tasks on perception and internal pronunciation of seven phonemes of the Russian language: A, B, F, G, M, R, U, which were presented visually (in the form of letters) and audibly. Th e analysis of the obtained EEG data was carried out using a new author’s method of localizing brain activity “virtually implanted electrode” (developed by A.V. Vartanov), which allows, according to scalp EEG data, to reconstruct electrical activity, the source of which is located in a certain place inside the head (activity was studied in 33 diff erent points of the brain). Results. Th e averaged evoked potentials were obtained for all the studied areas of the brain and the functional connections of these structures were revealed in the form of connectivity graphs for the corresponding conditions. Conclusions. It was found that the processes of pronunciation, expressed in EP, diff er depending on the modality of the initial form of the reproduced image — in visual perception, the supromarginal gyrus is more involved. Th e synchronized activity of a number of cerebral zones providing internal speech was revealed. A special role is played by the activity of the hippocampus and the pallidus (Gl. Palidus). Th e form of the EP when perceived is in many ways similar to its form when pronouncing. Activation at visual input is almost always signifi cantly higher than at auditory input.

Energy-Efficient Neural Network for Epileptic Seizure Prediction.

Seizure prediction for drug-refractory epilepsy patients can improve their quality of life, reduce their anxiety, and help them take the necessary precautions. Nowadays, numerous deep learning algorithms have been proposed to predict seizure onset and obtain better performance than traditional machine learning methods. However, these methods require a large set of parameters and large hardware resources; they also have high energy consumption. Therefore, these methods cannot be implemented on compact, low-power wearable, or implantable medical devices. The devices should operate on a real-time basis to continually inform the epileptic patients. In this paper, we describe energy-efficient and hardware-friendly methods to predict the epileptic seizures. A model of only 45 kB was obtained by the neural architecture search and was evaluated across three datasets. The overall sensitivity, false prediction rate, and area under receiver operating characteristic curve were 99.81%, 0.005/h, 1 and 93.48%, 0.063/h, 0.977 and 85.19%, 0.116/h, 0.933, respectively, for three public datasets. This model was further reduced with several methods for model compression. The performances for the model sizes less than 50 kB for scalp EEG data and less than 10 kB for intracranial EEG data outperformed all the other models of similar model sizes. In particular, the energy consumption estimation was less than 10 mJ per inference for scalp EEG signal and less than 0.5 mJ per inference for intracranial EEG signal, which meet the requirements for low-power wearable and implantable devices, respectively.

Deep Learning of Simultaneous Intracranial and Scalp EEG for Prediction, Detection, and Lateralization of Mesial Temporal Lobe Seizures.

In people with drug resistant epilepsy (DRE), seizures are unpredictable, often occurring with little or no warning. The unpredictability causes anxiety and much of the morbidity and mortality of seizures. In this work, 102 seizures of mesial temporal lobe onset were analyzed from 19 patients with DRE who had simultaneous intracranial EEG (iEEG) and scalp EEG as part of their surgical evaluation. The first aim of this paper was to develop machine learning models for seizure prediction and detection (i) using iEEG only, (ii) scalp EEG only and (iii) jointly analyzing both iEEG and scalp EEG. The second goal was to test if machine learning could detect a seizure on scalp EEG when that seizure was not detectable by the human eye (surface negative) but was seen in iEEG. The final question was to determine if the deep learning algorithm could correctly lateralize the seizure onset. The seizure detection and prediction problems were addressed jointly by training Deep Neural Networks (DNN) on 4 classes: non-seizure, pre-seizure, left mesial temporal onset seizure and right mesial temporal onset seizure. To address these aims, the classification accuracy was tested using two deep neural networks (DNN) against 3 different types of similarity graphs which used different time series of EEG data. The convolutional neural network (CNN) with the Waxman similarity graph yielded the highest accuracy across all EEG data (iEEG, scalp EEG and combined). Specifically, 1 second epochs of EEG were correctly assigned to their seizure, pre-seizure, or non-seizure category over 98% of the time. Importantly, the pre-seizure state was classified correctly in the vast majority of epochs (>97%). Detection from scalp EEG data alone of surface negative seizures and the seizures with the delayed scalp onset (the surface negative portion) was over 97%. In addition, the model accurately lateralized all of the seizures from scalp data, including the surface negative seizures. This work suggests that highly accurate seizure prediction and detection is feasible using either intracranial or scalp EEG data. Furthermore, surface negative seizures can be accurately predicted, detected and lateralized with machine learning even when they are not visible to the human eye.

Mapping Epileptic Networks Using Simultaneous Intracranial EEG-fMRI.

Background: Potentially curative epilepsy surgery can be offered if a single, discrete epileptogenic zone (EZ) can be identified. For individuals in whom there is no clear concordance between clinical localization, scalp EEG, and imaging data, intracranial EEG (icEEG) may be needed to confirm a predefined hypothesis regarding irritative zone (IZ), seizure onset zone (SOZ), and EZ prior to surgery. However, icEEG has limited spatial sampling and may fail to reveal the full extent of epileptogenic network if predefined hypothesis is not correct. Simultaneous icEEG-fMRI has been safely acquired in humans and allows exploration of neuronal activity at the whole-brain level related to interictal epileptiform discharges (IED) captured intracranially.Methods: We report icEEG-fMRI in eight patients with refractory focal epilepsy who had resective surgery and good postsurgical outcome. Surgical resection volume in seizure-free patients post-surgically reflects confirmed identification of the EZ. IEDs on icEEG were classified according to their topographic distribution and localization (Focal, Regional, Widespread, and Non-contiguous). We also divided IEDs by their location within the surgical resection volume [primary IZ (IZ1) IED] or outside [secondary IZ (IZ2) IED]. The distribution of fMRI blood oxygen level-dependent (BOLD) changes associated with individual IED classes were assessed over the whole brain using a general linear model. The concordance of resulting BOLD map was evaluated by comparing localization of BOLD clusters with surgical resection volume. Additionally, we compared the concordance of BOLD maps and presence of BOLD clusters in remote brain areas: precuneus, cuneus, cingulate, medial frontal, and thalamus for different IED classes.Results: A total of 38 different topographic IED classes were identified across the 8 patients: Focal (22) and non-focal (16, Regional = 9, Widespread = 2, Non-contiguous = 5). Twenty-nine IEDs originated from IZ1 and 9 from IZ2. All IED classes were associated with BOLD changes. BOLD maps were concordant with the surgical resection volume for 27/38 (71%) IED classes, showing statistical global maximum BOLD cluster or another cluster in the surgical resection volume. The concordance of BOLD maps with surgical resection volume was greater (p < 0.05) for non-focal (87.5%, 14/16) as compared to Focal (59%, 13/22) IED classes. Additionally, BOLD clusters in remote cortical and deep brain areas were present in 84% (32/38) of BOLD maps, more commonly (15/16; 93%) for non-focal IED-related BOLD maps.Conclusions: Simultaneous icEEG-fMRI can reveal BOLD changes at the whole-brain level for a wide range of IEDs on icEEG. BOLD clusters within surgical resection volume and remote brain areas were more commonly seen for non-focal IED classes, suggesting that a wider hemodynamic network is at play.

Interpretable Seizure Classification Using Unprocessed EEG With Multi-Channel Attentive Feature Fusion

Identification of seizure type plays a vital role during clinical diagnosis and treatment of epilepsy. However, the clinical evaluation of seizure type is highly dependent on the observed medical symptoms and the experience of the epileptologists who perform the evaluation. A key diagnostic tool is the electroencephalogram (EEG), which captures brain activity and can be used to determine the type of seizure occurring. EEG channels show non-stationary and dynamic behavior following the onset of a seizure event, and each EEG channel can display unique characteristics based on the seizure type and the epileptic foci. This paper proposes a novel deep learning architecture with attention-driven data fusion using raw scalp EEG data from a 10-20 layout, where independent shallow deep networks are trained on each channel. Unlike most state-of-the-art methods that first employ a data engineering step, we directly pass the EEG signal from each channel through a deep convolutional network consisting of SincNet and Conv1D layers, which learn robust features directly from the input signals, increasing model interpretability. However, the importance of each channel and the temporal information varies based on conditions particular to the recording, and this can adversely affect the overall recognition. We propose an approach based on the attentive fusion of channels to ensure only salient features from individual channel encoders are captured, passing the fused information to a Deep Neural Network for classification. Our proposed method has obtained an average F1-score of 0.967 on the Temple University Hospital Seizure Corpus, the largest publicly available seizure dataset.

Research on the influence of mental fatigue on information resources allocation of working memory

Mental fatigue is the subjective state of people after excessive consumption of information resources. Its impact on cognitive activities is mainly manifested as decreased alertness, poor memory and inattention, which is highly related to the performance after impaired working memory. In this paper, the partial directional coherence method was used to calculate the coherence coefficient of scalp electroencephalogram (EEG) of each electrode. The analysis of brain network and its attribute parameters was used to explore the changes of information resource allocation of working memory under mental fatigue. Mental fatigue was quickly induced by the experimental paradigm of adaptive N-back working memory. Twenty-five healthy college students were randomly recruited as subjects, including 14 males and 11 females, aged from 20 to 27 years old, all right-handed. The behavioral data and resting scalp EEG data were collected simultaneously. The results showed that the main information transmission pathway of the brain changed under mental fatigue, mainly in the frontal lobe and parietal lobe. The significant changes in brain network parameters indicated that the information transmission path of the brain decreased and the efficiency of information transmission decreased significantly. In the causal flow of each electrode and the information flow of each brain region, the inflow of information resources in the frontal lobe decreased under mental fatigue. Although the parietal lobe region and occipital lobe region became the main functional connection areas in the fatigue state, the inflow of information resources in these two regions was still reduced as a whole. These results indicated that mental fatigue affected the information resources allocation of working memory, especially in the frontal and parietal regions which were closely related to working memory.

Deep long short term memory based minimum variance kernel random vector functional link network for epileptic EEG signal classification

In this paper, the efficiently extracted and reduced features using deep long short-term memory (DLSTM) of the epileptic EEG signal integrated with minimum variance kernel random vector functional link net (MVKRVFLN) classifier are used to identify the seizure and non-seizure productively. Our methodology uses Children Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) multi-channel scalp EEG data, Bonn university single-channel intracranial EEG data, and two-channel Bern Barcelona intracranial EEG data recordings to assess the performance. The non-stationary, non-linear, complex, and chaotic type EEG signal is directly applied to DLSTM to obtain compressed significant features. The scatter plots of the DLSTM output features signify this compressed information are unique in nature. The excellent generalization ability, faster learning rate, simpler network-based MVKRVFLN classifier is formulated to well identify the seizure and non-seizure epochs precisely by applying the deep LSTM extracted discriminative features as input. The type of kernel function selection and choice of regularization coefficient are added information to improve the performance of the proposed approach. The suggested technique provides excellent classification accuracy, superior detection ability, faster speed, and insignificant false positive rate per hour, simpler structure, robustness to classify the seizure and non-seizure signals.

Electrophysiological Decoding of Spatial and Color Processing in Human Prefrontal Cortex

The prefrontal cortex (PFC) plays a pivotal role in goal-directed cognition, yet its representational code remains an open problem with decoding techniques ineffective in disentangling task-relevant variables from PFC. Here we applied regularized linear discriminant analysis to human scalp EEG data and were able to distinguish a mental-rotation task versus a color-perception task with 87% decoding accuracy. Dorsal and ventral areas in lateral PFC provided the dominant features dissociating the two tasks. Our findings show that EEG can reliably decode two independent task states from PFC and emphasize the PFC dorsal/ventral functional specificity in processing the where rotation task versus the what color task.

Automated detection of ripple oscillations in long-term scalp EEG from patients with infantile spasms

Objective. Scalp high-frequency oscillations (HFOs) are a promising biomarker of epileptogenicity in infantile spasms (IS) and many other epilepsy syndromes, but prior studies have relied on visual analysis of short segments of data due to the prevalence of artifacts in EEG. Here we set out to robustly characterize the rate and spatial distribution of HFOs in large datasets from IS subjects using fully automated HFO detection techniques. Approach. We prospectively collected long-term scalp EEG data from 12 subjects with IS and 18 healthy controls. For patients with IS, recording began prior to diagnosis and continued through initiation of treatment with adrenocorticotropic hormone (ACTH). The median analyzable EEG duration was 18.2 h for controls and 84.5 h for IS subjects (∼1300 h total). Ripples (80–250 Hz) were detected in all EEG data using an automated algorithm. Main results. HFO rates were substantially higher in patients with IS compared to controls. In IS patients, HFO rates were higher during sleep compared to wakefulness (median 5.5 min−1 and 2.9 min−1, respectively; p = 0.002); controls did not exhibit a difference in HFO rate between sleep and wakefulness (median 0.98 min−1 and 0.82 min−1, respectively). Spatially, IS patients exhibited significantly higher rates of HFOs in the posterior parasaggital region and significantly lower HFO rates in frontal channels, and this difference was more pronounced during sleep. In IS subjects, ACTH therapy significantly decreased the rate of HFOs. Significance. Here we provide a detailed characterization of the spatial distribution and rates of HFOs associated with IS, which may have relevance for diagnosis and assessment of treatment response. We also demonstrate that our fully automated algorithm can be used to detect HFOs in long-term scalp EEG with sufficient accuracy to clearly discriminate healthy subjects from those with IS.

Dynamic learning framework for epileptic seizure prediction using sparsity based EEG Reconstruction with Optimized CNN classifier

The World Health Organization (WHO) recently stated that epilepsy affects nearly 65 million people of the world population. Early forecast of the oncoming seizures is of paramount importance in saving the life of epileptic patients. This paper demonstrates a phase transition-based seizure prediction approach from multi-channel scalp electroencephalogram (EEG) recordings. The primary focus of this work is to discriminate the seizure and seizure-free EEG signals by learning the dynamics of preictal, interictal and ictal period. We propose an adaptive optimization approach using non-linear conjugate gradient technique in conjunction with Sparsity based EEG Reconstruction (SER) and three-dimensional Optimized Convolutional Neural Network (3D OCNN) classifier, based on Fletcher Reeves (FR) algorithm. Sparsity based artifact removal approach along with a 3D OCNN classifier, classifies the various states of seizures. FR algorithm is deployed with the deep neural network architecture to accelerate the convergence rate and to reduce the complexity of the proposed non-linear model. The Principle Component Analysis (PCA) algorithm replacing the Singular Value Decomposition (SVD) in the K-SVD algorithm, further reduces the time and complexity of the pre-processing stage. We further propose a Phase Transition based Kullback-Leibler divergence (PTB-KL) predictor for obtaining the Optimal Seizure Prediction Horizon (OSPH). The proposed model is evaluated using three diverse databases such as CHB-MIT, NINC and SRM respectively. Empirical results on the three EEG databases of 300 recordings outperforms the state-of-art approaches with an accuracy score of 0.98, sensitivity score of 0.99 and False Prediction Rate (FPR) of 0.07 FP/h. Statistical assessment of the proposed predictor gains an OSPH of about 1.1 h prior to the seizure onset. Experimental results prove that the phase transition-based seizure prediction approach is a promising one for accurate real-time prediction of epilepsy using scalp EEG data.

Phase Lag Analyses on Ictal Scalp Electroencephalography May Predict Outcomes of Corpus Callosotomy for Epileptic Spasms.

Objective: We aimed to clarify the patterns of ictal power and phase lag among bilateral hemispheres on scalp electroencephalography (EEG) recorded pre-operatively during epileptic spasms (ESs) and the correlation with the outcomes following corpus callosotomy.Methods: We enrolled 17 patients who underwent corpus callosotomy for ESs before 20 years of age. After corpus callosotomy, seven patients did not experience further ESs (favorable outcome group), and the remaining 10 patients had ongoing ESs (unfavorable outcome group). We used pre-operative scalp EEG data from monopolar montages using the average reference. The relative power spectrum (PS), ictal power laterality (IPL) among the hemispheres, and phase lag, calculated by the cross-power spectrum (CPS) among symmetrical electrodes (i.e., F3 and F4), were analyzed in the EEG data of ESs from 143 pre-operative scalp video-EEG records. Analyses were conducted separately in each frequency band from the delta, theta, alpha, beta, and gamma range. We compared the means of those data in each patient between favorable and unfavorable outcome groups.Results: Among all frequency bands, no significant differences were seen in the individual mean relative PSs in the favorable and unfavorable outcome group. Although the mean IPLs in each patient tended to be high in the unfavorable outcome group, no significant differences were found. The mean CPSs in the delta, theta, and gamma frequency bands were significantly higher in the unfavorable than in the favorable outcome group. Using the Youden index, the optimal cutoff points of those mean CPS values for unfavorable outcomes were 64.00 in the delta band (sensitivity: 100%, specificity: 80%), 74.20 in the theta band (100, 80%), and 82.05 in the gamma band (100, 80%). Subanalyses indicated that those CPS differences originated from pairs of symmetrical electrodes in the bilateral frontal and temporal areas.Significance: Ictal power and laterality of the ictal power in each frequency band were not associated with the outcomes of CC; however, the phase lags seen in the delta, theta, and gamma frequency bands were larger in the unfavorable than in the favorable outcome group. The phase lags may predict outcomes of CC for ESs on pre-surgical scalp-ictal EEGs.

Widespread Reductions of Spontaneous Neurophysiological Activity in Leber's Disease-An Application of EEG Source Current Density Reconstruction.

Leber’s hereditary optic neuropathy (LHON) is a rare, maternally inherited genetic disease caused by a mutation of mitochondrial DNA. Classical descriptions have highlighted structural abnormalities in various parts of patients’ optic tracts; however, current studies have proved that changes also affect many cortical and subcortical structures, not only these belonging to the visual system. This study aimed at improving our understanding of neurophysiological impairments in LHON. First of all, we wanted to know if there were any differences between the health control and LHON subjects in the whole-brain source electroencephalography (EEG) analysis. Second, we wanted to investigate the associations between the observed results and some selected aspects of Leber’s disease’s clinical picture. To meet these goals, 20 LHON patients and 20 age-matched healthy control (HC) subjects were examined. To investigate the electrophysiological differences between the HC and LHON groups, a quantitative analysis of the whole-brain current source density was performed. The signal analysis method was based on scalp EEG data and an inverse solution method called low-resolution brain electromagnetic tomography (eLORETA). In comparison with the healthy subjects, LHON participants showed significantly decreased neuronal activity in the alpha and gamma bands; more specifically, in the alpha band, the decrease was mainly found in the occipital lobes and secondary visual cortex, whereas, in the gamma band, the reduced activity occurred in multiple cortical areas. Additionally, a correlation was found between the alpha band activity of the right secondary visual cortex and the averaged thickness of the right retinal nerve fiber layer in the LHON participants. Our study suggests that LHON is associated with widespread cortical de-activation, rather than simply abnormalities of structures constituting the visual system.

RETRACTED ARTICLE: An optimized deep learning network model for EEG based seizure classification using synchronization and functional connectivity measures

Epilepsy is a brain disorder related to alteration in the nervous system which affects around 65 million people among the world’s population. Few works are focused on prediction of seizure relied on deep learning approaches, but the capability of optimal design has no longer been absolutely exploited. This work is focused on the seizure prediction obtained from long-short time records using optimized deep learning network model (ODLN). In this paper, the synchronization patterns and its feasibility of distinguishing the pre-ictal from inter-ictal states are examined by utilizing the interaction graph model as a functional connectivity measure. An optimized deep learning network with short- long-term memory is computed for the prediction of epileptic seizures occurrences. For, the modelling of ODLN, pre-analysis is performed with three modules and memory layers. It is finalized from these results; a two-layer ODLN is optimum to perform the epileptic seizure prediction for four different window sizes from 15 to 120 min. The assessment is implemented on the CHB-MIT Scalp EEG data set, providing 100% sensitivity and low false prediction rate ranges from 0.10 to 0.02 for seizure prediction. The proposed ODLN methodology reveals a notable increase in the performance rate of seizure prediction when compared with existing machine learning and Convolutional neural networks methods.

Analysis of Neuropsychiatric Symptoms in Patients with Alzheimer’s Disease Using Quantitative EEG and sLORETA

Objective: The electrocortical activities associated with the neuropsychiatric symptoms (NPSs) of Alzheimer’s disease (AD) were investigated using frequency-domain electroencephalography (EEG) spectral source analysis, and the potential electrocortical indices identified. Materials and Methods: Scalp EEG data were obtained from 51 patients with AD to investigate the presence of four NPS subdomains, hyperactivity, psychosis, affective symptoms, and apathy. EEG power spectra and the standardized low-resolution brain electromagnetic tomography (sLORETA)-localized EEG cortical sources were compared between the groups with and without the four NPS subdomains in eight frequency bands: 1–4, 4–8, 8–10, 10–12, 12–18, 18–20, 20–30, and 30–45 Hz. Results: The power spectral analysis of EEG data showed that AD patients with psychosis had lower values at the α₂-band in most areas. In patients with apathy, the θ-to-β power ratio showed a greater activity over the frontal and central regions. The cortical source analysis using sLORETA revealed that patients with psychosis showed decreased values in the α₂-band and patients with apathy showed higher δ-values, especially in the right frontal and temporal regions. Conclusion: The results of the present study showed that both classical EEG spectral and EEG source analysis could differentiate patients with and without NPSs, especially psychosis and apathy subdomains. Spectral and sLORETA analyses provided information helpful for a better characterization in patients with NPSs.

Delta-gamma phase-amplitude coupling as a biomarker of postictal generalized EEG suppression.

Postictal generalized EEG suppression is the state of suppression of electrical activity at the end of a seizure. Prolongation of this state has been associated with increased risk of sudden unexpected death in epilepsy, making characterization of underlying electrical rhythmic activity during postictal suppression an important step in improving epilepsy treatment. Phase-amplitude coupling in EEG reflects cognitive coding within brain networks and some of those codes highlight epileptic activity; therefore, we hypothesized that there are distinct phase-amplitude coupling features in the postictal suppression state that can provide an improved estimate of this state in the context of patient risk for sudden unexpected death in epilepsy. We used both intracranial and scalp EEG data from eleven patients (six male, five female; age range 21–41 years) containing 25 seizures, to identify frequency dynamics, both in the ictal and postictal EEG suppression states. Cross-frequency coupling analysis identified that during seizures there was a gradual decrease of phase frequency in the coupling between delta (0.5–4 Hz) and gamma (30+ Hz), which was followed by an increased coupling between the phase of 0.5–1.5 Hz signal and amplitude of 30–50 Hz signal in the postictal state as compared to the pre-seizure baseline. This marker was consistent across patients. Then, using these postictal-specific features, an unsupervised state classifier—a hidden Markov model—was able to reliably classify four distinct states of seizure episodes, including a postictal suppression state. Furthermore, a connectome analysis of the postictal suppression states showed increased information flow within the network during postictal suppression states as compared to the pre-seizure baseline, suggesting enhanced network communication. When the same tools were applied to the EEG of an epilepsy patient who died unexpectedly, ictal coupling dynamics disappeared and postictal phase-amplitude coupling remained constant throughout. Overall, our findings suggest that there are active postictal networks, as defined through coupling dynamics that can be used to objectively classify the postictal suppression state; furthermore, in a case study of sudden unexpected death in epilepsy, the network does not show ictal-like phase-amplitude coupling features despite the presence of convulsive seizures, and instead demonstrates activity similar to postictal. The postictal suppression state is a period of elevated network activity as compared to the baseline activity which can provide key insights into the epileptic pathology.