Functional brain connectivity from EEG in epilepsy: seizure prediction and epileptogenic focus localization

"Brain state network dynamics in pediatric epilepsy: Chaotic attractor transition ensemble network"

Traditional scalp EEG signal analysis in pediatric epilepsy is limited by poor spatial resolution, susceptibility to noise and artifacts, and difficulty in accurately localizing epileptic activity, especially from deep or interconnected brain regions. Additionally, such methods often overlook the dynamic nature of brain states and seizure propagation, while reliance on visual inspection introduces variability in interpretation. These limitations hinder precise seizure detection and the mechanistic understanding of brain network dynamics. Here, we offer an alternative approach that addresses these challenges, and eventually enables effective clinical interventions to improve patient outcomes. By incorporating chaos and dynamical systems theory, we present and validate a novel ensemble framework, Chaotic Attractor Transition Ensemble Network for Epilepsy (CATE-NET), which identifies neuro-dynamical signatures underlying pediatric epilepsy, facilitating the discrimination between physiological brain activity and seizure-induced signal irregularities. CATE-NET is modularly designed to leverage nonlinear dynamics of EEG signals and chaotic attractors, particularly the Rössler chaotic attractor to model scalp EEG data. This is followed by a long short-term memory network module for the automatic analysis of brain states. The final module utilizes probabilistic graphing to map the output of the LSTM to state transition graphs, between pre-ictal, inter-ictal, ictal, and ictal-free brain states. Model metrics include a classification accuracy of 0.98, sensitivity of 0.76, specificity of 0.84, and an AUC value of 0.91 when distinguishing among ictal, inter-ictal, and ictal-free brain states. Additionally, the system integrates flexible horizon windows of 10, 20, and 30 min to determine brain state transitions. We demonstrate that nonlinear dynamics present in epileptic brain states derived from the Rössler chaotic attractor are effective features to compute brain state analysis and visualize pediatric epileptic brain state topology. CATE-NET introduces a novel platform for brain state analysis, feature extraction, and topological mapping in pediatric epilepsy by combining chaotic attractors, deep learning, and probabilistic graphing. By integrating explainable AI (XAI), the framework clarifies how chaotic attractor patterns and probabilistic transitions contribute to brain state classifications, seizure state dynamic transitions. This approach reveals the spatial organization and EEG signal dynamics of pediatric epileptic brain states, allowing integration with clinical EEG equipment to potentially improve seizure management and real time decision making.

Enhancing non-invasive pre-surgical evaluation through functional connectivity and graph theory in drug-resistant focal epilepsy

BACKGROUND

Epilepsy, characterized as a network disorder, involves widely distributed areas following seizure propagation from a limited onset zone. Accurate delineation of the epileptogenic zone (EZ) is crucial for successful surgery in drug-resistant focal epilepsy. While visual analysis of scalp electroencephalogram (EEG) primarily elucidates seizure spreading patterns, we employed brain connectivity techniques and graph theory principles during the pre-ictal to ictal transition to define the epileptogenic network.

METHOD

Cortical sources were reconstructed from 40-channel scalp EEG in five patients during pre-surgical evaluation for focal drug-resistant epilepsy. Temporal Granger connectivity was estimated ten seconds before seizure and at seizure onset. Results have been analyzed using some centrality indices taken from Graph theory (Outdegree, Hubness). A new lateralization index is proposed by taking into account the sum of the most relevant hubness values across left and right regions of interest.

RESULTS

In three patients with positive surgical outcomes, analysis of the most relevant Hubness regions closely aligned with clinical hypotheses, demonstrating consistency in EZ lateralization and location. In one patient, the method provides unreliable results due to the abundant movement artifacts preceding the seizure. In a fifth patient with poor surgical outcome, the proposed method suggests a wider epileptic network compared with the clinically suspected EZ, providing intriguing new indications beyond those obtained with traditional electro-clinical analysis.

CONCLUSIONS

The proposed method could serve as an additional tool during pre-surgical non-invasive evaluation, complementing data obtained from EEG visual inspection. It represents a first step toward a more sophisticated analysis of seizure onset based on connectivity imbalances, electrical propagation, and graph theory principles.

A comparative study between a power and a connectivity sEEG biomarker for seizure-onset zone identification in temporal lobe epilepsy

BACKGROUND

Ictal stereo-encephalography (sEEG) biomarkers for seizure onset zone (SOZ) localization can be classified depending on whether they target abnormalities in signal power or functional connectivity between signals, and they may depend on the frequency band and time window at which they are estimated.

NEW METHOD

This work aimed to compare and optimize the performance of a power and a connectivity-based biomarker to identify SOZ contacts from ictal sEEG recordings. To do so, we used a previously introduced power-based measure, the normalized mean activation (nMA), which quantifies the ictal average power activation. Similarly, we defined the normalized mean strength (nMS), to quantify the ictal mean functional connectivity of every contact with the rest. The optimal frequency bands and time windows were selected based on optimizing AUC and F2-score.

RESULTS

The analysis was performed on a dataset of 67 seizures from 10 patients with pharmacoresistant temporal lobe epilepsy. Our results suggest that the power-based biomarker generally performs better for the detection of SOZ than the connectivity-based one. However, an equivalent performance level can be achieved when both biomarkers are independently optimized. Optimal performance was achieved in the beta and lower-gamma range for the power biomarker and in the lower- and higher-gamma range for connectivity, both using a 20 or 30 s period after seizure onset.

CONCLUSIONS

The results of this study highlight the importance of this optimization step over frequency and time windows when comparing different SOZ discrimination biomarkers. This information should be considered when training SOZ classifiers on retrospective patients' data for clinical applications.

Interictal stereo-electroencephalography features below 45 Hz are sufficient for correct localization of the epileptogenic zone and postsurgical outcome prediction

OBJECTIVE

Evidence suggests that the most promising results in interictal localization of the epileptogenic zone (EZ) are achieved by a combination of multiple stereo-electroencephalography (SEEG) biomarkers in machine learning models. These biomarkers usually include SEEG features calculated in standard frequency bands, but also high-frequency (HF) bands. Unfortunately, HF features require extra effort to record, store, and process. Here we investigate the added value of these HF features for EZ localization and postsurgical outcome prediction.

METHODS

In 50 patients we analyzed 30 min of SEEG recorded during non-rapid eye movement sleep and tested a logistic regression model with three different sets of features. The first model used broadband features (1-500 Hz); the second model used low-frequency features up to 45 Hz; and the third model used HF features above 65 Hz. The EZ localization by each model was evaluated by various metrics including the area under the precision-recall curve (AUPRC) and the positive predictive value (PPV). The differences between the models were tested by the Wilcoxon signed-rank tests and Cliff's Delta effect size. The differences in outcome predictions based on PPV values were further tested by the McNemar test.

RESULTS

The AUPRC score of the random chance classifier was .098. The models (broad-band, low-frequency, high-frequency) achieved median AUPRCs of .608, .582, and .522, respectively, and correctly predicted outcomes in 38, 38, and 33 patients. There were no statistically significant differences in AUPRC or any other metric between the three models. Adding HF features to the model did not have any additional contribution.

SIGNIFICANCE

Low-frequency features are sufficient for correct localization of the EZ and outcome prediction with no additional value when considering HF features. This finding allows significant simplification of the feature calculation process and opens the possibility of using these models in SEEG recordings with lower sampling rates, as commonly performed in clinical routines.

Increased coherence predicts medical refractoriness in patients with temporal lobe epilepsy on monotherapy

Among patients with epilepsy, 30-40% experience recurrent seizures even after adequate antiseizure medications therapies, making them refractory. The early identification of refractory epilepsy is important to provide timely surgical treatment for these patients. In this study, we analyze interictal electroencephalography (EEG) data to predict drug refractoriness in patients with temporal lobe epilepsy (TLE) who were treated with monotherapy at the time of the first EEG acquisition. Various EEG features were extracted, including statistical measurements and interchannel coherence. Feature selection was performed to identify the optimal features, and classification was conducted using different classifiers. Functional connectivity and graph theory measurements were calculated to identify characteristics of refractory TLE. Among the 48 participants, 34 (70.8%) were responsive, while 14 (29.2%) were refractory over a mean follow-up duration of 38.5 months. Coherence feature within the gamma frequency band exhibited the most favorable performance. The light gradient boosting model, employing the mutual information filter-based feature selection method, demonstrated the highest performance (AUROC = 0.821). Compared to the responsive group, interchannel coherence displayed higher values in the refractory group. Interestingly, graph theory measurements using EEG coherence exhibited higher values in the refractory group than in the responsive group. Our study has demonstrated a promising method for the early identification of refractory TLE utilizing machine learning algorithms.

Research on mental fatigue during long-term motor imagery: a pilot study

Mental fatigue during long-term motor imagery (MI) may affect intention recognition in MI applications. However, the current research lacks the monitoring of mental fatigue during MI and the definition of robust biomarkers. The present study aims to reveal the effects of mental fatigue on motor imagery recognition at the brain region level and explore biomarkers of mental fatigue. To achieve this, we recruited 10 healthy participants and asked them to complete a long-term motor imagery task involving both right- and left-handed movements. During the experiment, we recorded 32-channel EEG data and carried out a fatigue questionnaire for each participant. As a result, we found that mental fatigue significantly decreased the subjects' motor imagery recognition rate during MI. Additionally the theta power of frontal, central, parietal, and occipital clusters significantly increased after the presence of mental fatigue. Furthermore, the phase synchronization between the central cluster and the frontal and occipital lobes was significantly weakened. To summarize, the theta bands of frontal, central, and parieto-occipital clusters may serve as powerful biomarkers for monitoring mental fatigue during motor imagery. Additionally, changes in functional connectivity between the central cluster and the prefrontal and occipital lobes during motor imagery could be investigated as potential biomarkers.

Thermodynamic model for memory

A thermodynamic model for memory formation is proposed. Key points include: 1) Any thought or consciousness corresponds to a thermodynamic system of nerve cells. 2) The system concept of nerve cells can only be described by thermodynamics of condensed matter. 3) The memory structure is logically associated with the system structure or the normal structure of biology. 4) The development of our thoughts is processed irreversibly, and numerous states or thoughts can be generated. 5) Memory formation results from the reorganization and change of cellular structures (or memory structures), which are related to nerve cell skeleton and membrane. Their alteration can change the excitability of nerve cells and the pathway of neural impulse conduction. 6) Amnesia results from the loss of thermodynamic stability of the memory structure, which can be achieved by different ways. Some related phenomena and facts are discussed. The analysis shows that thermodynamics can account for the basic properties of memory.

Prospects of Electrocorticography in Neuropharmacological Studies in Small Laboratory Animals

Electrophysiological methods of research are widely used in neurobiology. To assess the bioelectrical activity of the brain in small laboratory animals, electrocorticography (ECoG) is most often used, which allows the recording of signals directly from the cerebral cortex. To date, a number of methodological approaches to the manufacture and implantation of ECoG electrodes have been proposed, the complexity of which is determined by experimental tasks and logistical capabilities. Existing methods for analyzing bioelectrical signals are used to assess the functional state of the nervous system in test animals, as well as to identify correlates of pathological changes or pharmacological effects. The review presents current areas of applications of ECoG in neuropharmacological studies in small laboratory animals. Traditionally, this method is actively used to study the antiepileptic activity of new molecules. However, the possibility of using ECoG to assess the neuroprotective activity of drugs in models of traumatic, vascular, metabolic, or neurodegenerative CNS damage remains clearly underestimated. Despite the fact that ECoG has a number of disadvantages and methodological difficulties, the recorded data can be a useful addition to traditional molecular and behavioral research methods. An analysis of the works in recent years indicates a growing interest in the method as a tool for assessing the pharmacological activity of psychoactive drugs, especially in combination with classification and prediction algorithms.

Emotion brain network topology in healthy subjects following passive listening to different auditory stimuli

A large body of research establishes the efficacy of musical intervention in many aspects of physical, cognitive, communication, social, and emotional rehabilitation. However, the underlying neural mechanisms for musical therapy remain elusive. This study aimed to investigate the potential neural correlates of musical therapy, focusing on the changes in the topology of emotion brain network. To this end, a Bayesian statistical approach and a cross-over experimental design were employed together with two resting-state magnetoencephalography (MEG) as controls. MEG recordings of 30 healthy subjects were acquired while listening to five auditory stimuli in random order. Two resting-state MEG recordings of each subject were obtained, one prior to the first stimulus (pre) and one after the final stimulus (post). Time series at the level of brain regions were estimated using depth-weighted minimum norm estimation (wMNE) source reconstruction method and the functional connectivity between these regions were computed. The resultant connectivity matrices were used to derive two topological network measures: transitivity and global efficiency which are important in gauging the functional segregation and integration of brain network respectively. The differences in these measures between pre- and post-stimuli resting MEG were set as the equivalence regions. We found that the network measures under all auditory stimuli were equivalent to the resting state network measures in all frequency bands, indicating that the topology of the functional brain network associated with emotional regulation in healthy subjects remains unchanged following these auditory stimuli. This suggests that changes in the emotion network topology may not be the underlying neural mechanism of musical therapy. Nonetheless, further studies are required to explore the neural mechanisms of musical interventions especially in the populations with neuropsychiatric disorders.

Effects of gender and age on sleep EEG functional connectivity differences in subjects with mild difficulty falling asleep

Introduction

Difficulty falling asleep place an increasing burden on society. EEG-based sleep staging is fundamental to the diagnosis of sleep disorder, and the selection of features for each sleep stage is a key step in the sleep analysis. However, the differences of sleep EEG features in gender and age are not clear enough.

Methods

This study aimed to investigate the effects of age and gender on sleep EEG functional connectivity through statistical analysis of brain functional connectivity and machine learning validation. The two-overnight sleep EEG data of 78 subjects with mild difficulty falling asleep were categorized into five sleep stages using markers and segments from the "sleep-EDF" public database. First, the 78 subjects were finely grouped, and the mutual information of the six sleep EEG rhythms of δ, θ, α, β, spindle, and sawtooth wave was extracted as a functional connectivity measure. Then, one-way analysis of variance (ANOVA) was used to extract significant differences in functional connectivity of sleep rhythm waves across sleep stages with respect to age and gender. Finally, machine learning algorithms were used to investigate the effects of fine grouping of age and gender on sleep staging.

Results and discussion

The results showed that: (1) The functional connectivity of each sleep rhythm wave differed significantly across sleep stages, with delta and beta functional connectivity differing significantly across sleep stages. (2) Significant differences in functional connections among young and middle-aged groups, and among young and elderly groups, but no significant difference between middle-aged and elderly groups. (3) Female functional connectivity strength is generally higher than male at the high-frequency band of EEG, but no significant difference in the low-frequency. (4) Finer group divisions based on gender and age can indeed improve the accuracy of sleep staging, with an increase of about 3.58% by using the random forest algorithm. Our results further reveal the electrophysiological neural mechanisms of each sleep stage, and find that sleep functional connectivity differs significantly in both gender and age, providing valuable theoretical guidance for the establishment of automated sleep stage models.

Investigation of the Effect of Physiological Artifacts on Task-based Functional Connectivity: A Simulation Study

Functional connectivity is commonly used for studying functional interactions among brain regions. However, its results are affected by noise and/or physiological artifacts, especially when computed using blood-oxygen-level-dependent (BOLD) functional magnetic resonance imaging (fMRI) signals. In this study, we assessed the effect of these artifacts by simulating physiological and BOLD fMRI signals during resting and task conditions and quantifying the resulting functional connectivity results patterns by well established methods (full and partial correlation). Our results reveal that the regions with similar physiological response functions were adversely affected by physiological artifacts. Notably, functional connectivity values computed during task execution exhibited lower errors compared to those computed during the rest period. Furthermore, the results computed using the partial correlation method consistently yielded lower errors compared to those computed using full correlation. Overall, our findings quantitatively characterize the impact of physiological artifacts on functional connectivity patterns and emphasize the importance of method choice in mitigating the impact of artifacts.

Phase coherence-A time-localized approach to studying interactions

Coherence measures the similarity of progression of phases between oscillations or waves. When applied to multi-scale, nonstationary dynamics with time-varying amplitudes and frequencies, high values of coherence provide a useful indication of interactions, which might otherwise go unnoticed. However, the choice of analyzing coherence based on phases and amplitudes (amplitude-weighted phase coherence) vs only phases (phase coherence) has long been seen as arbitrary. Here, we review the concept of coherence and focus on time-localized methods of analysis, considering both phase coherence and amplitude-weighted phase coherence. We discuss the importance of using time-localized analysis and illustrate the methods and their practicalities on both numerically modeled and real time-series. The results show that phase coherence is more robust than amplitude-weighted phase coherence to both noise perturbations and movement artifacts. The results also have wider implications for the analysis of real data and the interpretation of physical systems.

Seizure onset zone (SOZ) identification using effective brain connectivity of epileptogenic networks

Objective. To demonstrate the capability of utilizing graph feature-based supervised machine learning (ML) algorithm on intracranial electroencephalogram recordings for the identification of seizure onset zones (SOZs) in individuals with drug-resistant epilepsy.Approach. Utilizing three model-free measures of effective connectivity (EC)-directed information, mutual information-guided Granger causality index (MI-GCI), and frequency-domain convergent cross-mapping (FD-CCM) - directed graphs are generated. Graph centrality measures at different sparsity are used as the classifier's features.Main results. The centrality features achieve high accuracies exceeding 90% in distinguishing SOZ electrodes from non-SOZ electrodes. Notably, a sparse graph representation with just ten features and simple ML models effectively achieves such performance. The study identifies FD-CCM centrality measures as particularly significant, with a mean AUC of 0.93, outperforming prior literature. The FD-CCM-based graph modeling also highlights elevated centrality measures among SOZ electrodes, emphasizing heightened activity relative to non-SOZ electrodes during ictogenesis.Significance. This research not only underscores the efficacy of automated SOZ identification but also illuminates the potential of specific EC measures in enhancing discriminative power within the context of epilepsy research.

Electroencephalogram synchronization measure as a predictive biomarker of Vagus nerve stimulation response in refractory epilepsy: A retrospective study

There are currently no established biomarkers for predicting the therapeutic effectiveness of Vagus Nerve Stimulation (VNS). Given that neural desynchronization is a pivotal mechanism underlying VNS action, EEG synchronization measures could potentially serve as predictive biomarkers of VNS response. Notably, an increased brain synchronization in delta band has been observed during sleep-potentially due to an activation of thalamocortical circuitry, and interictal epileptiform discharges are more frequently observed during sleep. Therefore, investigation of EEG synchronization metrics during sleep could provide a valuable insight into the excitatory-inhibitory balance in a pro-epileptogenic state, that could be pathological in patients exhibiting a poor response to VNS. A 19-channel-standard EEG system was used to collect data from 38 individuals with Drug-Resistant Epilepsy (DRE) who were candidates for VNS implantation. An EEG synchronization metric-the Weighted Phase Lag Index (wPLI)-was extracted before VNS implantation and compared between sleep and wakefulness, and between responders (R) and non-responders (NR). In the delta band, a higher wPLI was found during wakefulness compared to sleep in NR only. However, in this band, no synchronization difference in any state was found between R and NR. During sleep and within the alpha band, a negative correlation was found between wPLI and the percentage of seizure reduction after VNS implantation. Overall, our results suggest that patients exhibiting a poor VNS efficacy may present a more pathological thalamocortical circuitry before VNS implantation. EEG synchronization measures could provide interesting insights into the prerequisites for responding to VNS, in order to avoid unnecessary implantations in patients showing a poor therapeutic efficacy.

TSANN-TG: Temporal-Spatial Attention Neural Networks with Task-Specific Graph for EEG Emotion Recognition

Electroencephalography (EEG)-based emotion recognition is increasingly pivotal in the realm of affective brain-computer interfaces. In this paper, we propose TSANN-TG (temporal-spatial attention neural network with a task-specific graph), a novel neural network architecture tailored for enhancing feature extraction and effectively integrating temporal-spatial features. TSANN-TG comprises three primary components: a node-feature-encoding-and-adjacency-matrices-construction block, a graph-aggregation block, and a graph-feature-fusion-and-classification block. Leveraging the distinct temporal scales of features from EEG signals, TSANN-TG incorporates attention mechanisms for efficient feature extraction. By constructing task-specific adjacency matrices, the graph convolutional network with an attention mechanism captures the dynamic changes in dependency information between EEG channels. Additionally, TSANN-TG emphasizes feature integration at multiple levels, leading to improved performance in emotion-recognition tasks. Our proposed TSANN-TG is applied to both our FTEHD dataset and the publicly available DEAP dataset. Comparative experiments and ablation studies highlight the excellent recognition results achieved. Compared to the baseline algorithms, TSANN-TG demonstrates significant enhancements in accuracy and F1 score on the two benchmark datasets for four types of cognitive tasks. These results underscore the significant potential of the TSANN-TG method to advance EEG-based emotion recognition.

Timing matters for accurate identification of the epileptogenic zone

OBJECTIVE

Interictal biomarkers of the epileptogenic zone (EZ) and their use in machine learning models open promising avenues for improvement of epilepsy surgery evaluation. Currently, most studies restrict their analysis to short segments of intracranial EEG (iEEG).

METHODS

We used 2381 hours of iEEG data from 25 patients to systematically select 5-minute segments across various interictal conditions. Then, we tested machine learning models for EZ localization using iEEG features calculated within these individual segments or across them and evaluated the performance by the area under the precision-recall curve (PRAUC).

RESULTS

On average, models achieved a score of 0.421 (the result of the chance classifier was 0.062). However, the PRAUC varied significantly across the segments (0.323-0.493). Overall, NREM sleep achieved the highest scores, with the best results of 0.493 in N2. When using data from all segments, the model performed significantly better than single segments, except NREM sleep segments.

CONCLUSIONS

The model based on a short segment of iEEG recording can achieve similar results as a model based on prolonged recordings. The analyzed segment should, however, be carefully and systematically selected, preferably from NREM sleep.

SIGNIFICANCE

Random selection of short iEEG segments may give rise to inaccurate localization of the EZ.

Epileptic seizure prediction based on features extracted from lagged Poincaré plots

OBJECTIVE

The present work proposes a new epileptic seizure prediction method based on lagged Poincaré plot analysis of heart rate (HR).

METHODS

In this article, the Poincaré plots with six different lags (1-6) were constructed for four episodes of heart rate variability (HRV) before the seizures. Moreover, two features were extracted based on lagged Poincare plots, which include the angle between the time series and the ellipse density fitted to the RR points.

RESULTS

The proposed method was applied to 16 epileptic patients with 170 seizures. The results included sensitivity of 80.42% for the angle feature and 75.19% for the density feature. The false-positive rate was 0.15/Hr, which indicates that the system has superiority over the random predictor.

CONCLUSION

The proposed HRV-based epileptic seizure prediction method has the potential to be used in daily life because HR can be measured easily by using a wearable sensor.

Comparison between epileptic seizure prediction and forecasting based on machine learning

Epilepsy affects around 1% of the population worldwide. Anti-epileptic drugs are an excellent option for controlling seizure occurrence but do not work for around one-third of patients. Warning devices employing seizure prediction or forecasting algorithms could bring patients new-found comfort and quality of life. These algorithms would attempt to detect a seizure's preictal period, a transitional moment between regular brain activity and the seizure, and relay this information to the user. Over the years, many seizure prediction studies using Electroencephalogram-based methodologies have been developed, triggering an alarm when detecting the preictal period. Recent studies have suggested a shift in view from prediction to forecasting. Seizure forecasting takes a probabilistic approach to the problem in question instead of the crisp approach of seizure prediction. In this field of study, the triggered alarm to symbolize the detection of a preictal period is substituted by a constant risk assessment analysis. The present work aims to explore methodologies capable of seizure forecasting and establish a comparison with seizure prediction results. Using 40 patients from the EPILEPSIAE database, we developed several patient-specific prediction and forecasting algorithms with different classifiers (a Logistic Regression, a 15 Support Vector Machines ensemble, and a 15 Shallow Neural Networks ensemble). Results show an increase of the seizure sensitivity in forecasting relative to prediction of up to 146% and in the number of patients that displayed an improvement over chance of up to 300%. These results suggest that a seizure forecasting methodology may be more suitable for seizure warning devices than a seizure prediction one.

Network alterations in temporal lobe epilepsy during non-rapid eye movement sleep and wakefulness

OBJECTIVE

Investigate sleep and temporal lobe epilepsy (TLE) effects on brain networks derived from electroencephalography (EEG).

METHODS

High-density EEG was recorded during non-rapid eye movement (NREM) sleep stage 2 (N2) and wakefulness in 23 patients and healthy controls (HC). Epochs without epileptic discharges were source-reconstructed in 72 brain regions and connectivity was estimated. We calculated network integration and segregation at global (global efficiency, GE; average clustering coefficient, avgCC) and hemispheric level. These were compared between groups across frequency bands and correlated with the individual proportion of wakefulness- or sleep-related seizures.

RESULTS

At the global level, patients had higher delta GE, delta avgCC and theta avgCC than controls, irrespective of the vigilance state. During wakefulness, theta GE of patients was higher than controls and, for patients, theta GE during wakefulness was higher than during N2. Wake-to-sleep differences in TLE were notable only in the ipsilateral hemisphere. Only measures from wakefulness recordings correlated with the proportion of wakefulness- or sleep-related seizures.

CONCLUSIONS

TLE network alterations are more prominent during wakefulness and at lower frequencies. Increased integration and segregation suggest a pathological 'small world' configuration with a possible inhibitory role.

SIGNIFICANCE

Network alterations in TLE occur and are easier to detect during wakefulness.

DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG

Major Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide. Making early and accurate diagnosis of it is very meaningful. Recently, EEG, a non-invasive technique of recording spontaneous electrical activity of brains, has been widely used for MDD diagnosis. However, there are still some challenges in data quality and data size of EEG: (1) A large amount of noise is inevitable during EEG collection, making it difficult to extract discriminative features from raw EEG; (2) It is difficult to recruit a large number of subjects to collect sufficient and diverse data for model training. Both of the challenges cause the overfitting problem, especially for deep learning methods. In this paper, we propose DiffMDD, a diffusion-based deep learning framework for MDD diagnosis using EEG. Specifically, we extract more noise-irrelevant features to improve the model's robustness by designing the Forward Diffusion Noisy Training Module. Then we increase the size and diversity of data to help the model learn more generalized features by designing the Reverse Diffusion Data Augmentation Module. Finally, we re-train the classifier on the augmented dataset for MDD diagnosis. We conducted comprehensive experiments to test the overall performance and each module's effectiveness. The framework was validated on two public MDD diagnosis datasets, achieving the state-of-the-art performance.

An evaluation of inter-brain EEG coupling methods in hyperscanning studies

EEG-based hyperscanning technology has been increasingly applied to analyze interpersonal interactions in social neuroscience in recent years. However, different methods are employed in various of studies without a complete investigation of the suitability of these methods. Our study aimed to systematically compare typical inter-brain EEG coupling methods, with simulated EEG data generated by real EEG data. In particular, two critical metrics of noise level and time delay were manipulated, and three different coupling models were tested. The results revealed that: (1) under certain conditions, various methods were leveraged by noise level and time delay, leading to different performances; (2) most algorithms achieved better experimental results and performance under high coupling degree; (3) with our simulation process, temporal and spectral models showed relatively good results, while data simulated with phase coupling model performed worse. This is the first systematic comparison of typical inter-brain EEG coupling methods, with simulated EEG data generated by real EEG data from different subjects. Existing methods mainly focused on intra-brain coupling. To our knowledge, there was only one previous study that compared five inter-brain EEG coupling methods (Burgess in Front Human Neurosci 7:881, 2013). However, the simulated data used in this study were generated time series with varied degrees of phase coupling without considering any EEG characteristics. For future research, appropriate methods need to be selected based on possible underlying mechanisms (temporal, spectral and phase coupling model hypothesis) of a specific study, as well as the expected coupling degree and conditions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09911-1.

The time-evolving epileptic brain network: concepts, definitions, accomplishments, perspectives

Epilepsy is now considered a network disease that affects the brain across multiple levels of spatial and temporal scales. The paradigm shift from an epileptic focus-a discrete cortical area from which seizures originate-to a widespread epileptic network-spanning lobes and hemispheres-considerably advanced our understanding of epilepsy and continues to influence both research and clinical treatment of this multi-faceted high-impact neurological disorder. The epileptic network, however, is not static but evolves in time which requires novel approaches for an in-depth characterization. In this review, we discuss conceptual basics of network theory and critically examine state-of-the-art recording techniques and analysis tools used to assess and characterize a time-evolving human epileptic brain network. We give an account on current shortcomings and highlight potential developments towards an improved clinical management of epilepsy.

Dementia classification using a graph neural network on imaging of effective brain connectivity

Alzheimer's disease (AD) and Parkinson's disease (PD) are two of the most common forms of neurodegenerative diseases. The literature suggests that effective brain connectivity (EBC) has the potential to track differences between AD, PD and healthy controls (HC). However, how to effectively use EBC estimations for the research of disease diagnosis remains an open problem. To deal with complex brain networks, graph neural network (GNN) has been increasingly popular in very recent years and the effectiveness of combining EBC and GNN techniques has been unexplored in the field of dementia diagnosis. In this study, a novel directed structure learning GNN (DSL-GNN) was developed and performed on the imaging of EBC estimations and power spectrum density (PSD) features. In comparison to the previous studies on GNN, our proposed approach enhanced the functionality for processing directional information, which builds the basis for more efficiently performing GNN on EBC. Another contribution of this study is the creation of a new framework for applying univariate and multivariate features simultaneously in a classification task. The proposed framework and DSL-GNN are validated in four discrimination tasks and our approach exhibited the best performance, against the existing methods, with the highest accuracy of 94.0% (AD vs. HC), 94.2% (PD vs. HC), 97.4% (AD vs. PD) and 93.0% (AD vs. PD vs. HC). In a word, this research provides a robust analytical framework to deal with complex brain networks containing causal directional information and implies promising potential in the diagnosis of two of the most common neurodegenerative conditions.

The applied principles of EEG analysis methods in neuroscience and clinical neurology

Electroencephalography (EEG) is a non-invasive measurement method for brain activity. Due to its safety, high resolution, and hypersensitivity to dynamic changes in brain neural signals, EEG has aroused much interest in scientific research and medical fields. This article reviews the types of EEG signals, multiple EEG signal analysis methods, and the application of relevant methods in the neuroscience field and for diagnosing neurological diseases. First, three types of EEG signals, including time-invariant EEG, accurate event-related EEG, and random event-related EEG, are introduced. Second, five main directions for the methods of EEG analysis, including power spectrum analysis, time-frequency analysis, connectivity analysis, source localization methods, and machine learning methods, are described in the main section, along with different sub-methods and effect evaluations for solving the same problem. Finally, the application scenarios of different EEG analysis methods are emphasized, and the advantages and disadvantages of similar methods are distinguished. This article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives, provide references for subsequent research, and summarize current issues and prospects for the future.

SEEG-based epileptic seizure network modeling and analysis for pre-surgery evaluation

Stereo-electroencephalography is a minimally invasive technique for patients with refractory epilepsy pursuing surgery to reduce or control seizures. Electrodes are implanted based on pre-surgery evaluations and can collect deep brain activities for surgery decisions. This paper presents a methodology to analyze stereo-electroencephalography and assist clinicians by recommending the optimal surgical option and target areas for focal epilepsy patients. A seizure network (graph) model is proposed to characterize the spatial distribution and temporal changes of ictal events. The network nodes and edges correspond to specific epileptogenic regions and propagation/impact pathways (weighted by directed transfer function), respectively. We then employ a K-means clustering strategy to group nodes into a few clusters, from which the target surgical areas can be identified. Ten patients with different types of focal seizures were thoroughly analyzed. Promising consistency between results of our method's recommendations, clinical decisions and surgery outcomes were observed.

Seizure onset zone identification using phase-amplitude coupling and multiple machine learning approaches for interictal electrocorticogram

Automatic seizure onset zone (SOZ) localization using interictal electrocorticogram (ECoG) improves the diagnosis and treatment of patients with medically refractory epilepsy. This study aimed to investigate the characteristics of phase-amplitude coupling (PAC) extracted from interictal ECoG and the feasibility of PAC serving as a promising biomarker for SOZ identification. We employed the mean vector length modulation index approach on the 20-s ECoG window to calculate PAC features between low-frequency rhythms (0.5-24 Hz) and high frequency oscillations (HFOs) (80-560 Hz). We used statistical measures to test the significant difference in PAC between the SOZ and non-seizure onset zone (NSOZ). To overcome the drawback of handcraft feature engineering, we established novel machine learning models to learn automatically the characteristics of the obtained PAC features and classify them to identify the SOZ. Besides, to handle imbalanced dataset classification, we introduced novel feature-wise/class-wise re-weighting strategies in conjunction with classifiers. In addition, we proposed a time-series nest cross-validation to provide more accurate and unbiased evaluations for this model. Seven patients with focal cortical dysplasia were included in this study. The experiment results not only showed that a significant coupling at band pairs of slow waves and HFOs exists in the SOZ when compared with the NSOZ, but also indicated the effectiveness of the PAC features and the proposed models in achieving better classification performance .

SEEG-based reevaluation of epileptogenic networks and the predictive role for reoperation in MTLE patients with surgical failure

OBJECTIVE

Approximately 20%-30% of mesial temporal lobe epilepsy (MTLE) patients got unfavorable seizure control after surgery, and there was a discrepancy about the reasons for the surgical failure. The functional connectivity (FC) patterns obtained from stereo-electroencephalography (SEEG) reveal information about the dynamics of the epileptic brain and the added value of extracting information that was not identifiable in the SEEG data using FC analysis. This study aims to find out the patterns of the potential epileptogenic network of failure patients and the electrophysiological predictors of reoperation.

METHODS

From January 2012 to December 2019, the MTLE patients with surgical failure were reviewed, and all patients underwent SEEG-guided reoperation. The epileptogenic network was quantified by calculating FC indicators, including phase slope index (PSI), mutual information (MI) strength, imaginary coherence (icoh), and Granger causality.

RESULTS

Ten patients with 13 seizures were included in the analysis, and 7 of them achieved a favorable outcome after the SEEG-guided reoperation. The surgical zone (SZ) with a favorable prognosis showed greater outward information flow than the non-SZ, whereas the SZ with an unfavorable prognosis showed greater inward information flow. The recurrent patients with favorable prognosis had strong connectivity between the posterior hippocampus, temporal neocortex, and insula, whereas the patients with unfavorable prognosis showed strong functional connectivity between the insula and temporal-parietal-occipital junction. The power spectrum of patients with favorable prognosis was significantly lower than that of patients with unfavorable prognosis, especially showing a more oscillation power of low frequency.

SIGNIFICANCE

The SEEG-guided reoperation could achieve favorable seizure control outcomes for recurrent patients. The FCs were a potential indicator to help construct the temporal epileptic network and predictor for the reoperative prognosis in the recurrent patients.

Weighted ordinal connection based functional network classification for schizophrenia disease detection using EEG signal

A brain connectivity network (BCN) is an advanced approach to examining brain functionality in various conditions. However, the predictability of the BCN is affected by the connectivity measure used for the network construction. Various connectivity measures available in the literature differ according to the domain of their working data. The application of random connectivity measures might result in an inefficient BCN that ultimately hampers its predictability. Therefore, selecting an appropriate functional connectivity metric is crucial in clinical as well as cognitive neuroscience. In parallel to this, an effective network identifier plays a vital role in distinguishing different brain states. Hence, the objective of this paper is two-fold, which includes identifying suitable connectivity measures and proposing an efficient network identifier. For this, the weighted BCN (WBCN) is constructed using multiple connectivity measures like correlation coefficient (r), coherence (COH), phase-locking value (PLV), and mutual information (MI) from electroencephalogram (EEG) signals. The most recent technique for feature extraction, i.e., weighted ordinal connections, has been applied to EEG-based BCN. EEG signals data has been taken from the schizophrenia disease database. Further, several classification algorithms such as k-nearest neighbours (KNN), support vector machine (SVM) with linear, radial basis function and polynomial kernels, random forest (RF), and 1D convolutional neural network (CNN1D) are used to classify the brain states based on extracted features. In classification, 90% accuracy is achieved by the CNN1D classifier with WBCN based on the coherence connectivity measure. The study also provides a structural analysis of the BCN.

Functional connectivity discriminates epileptogenic states and predicts surgical outcome in children with drug resistant epilepsy

Normal brain functioning emerges from a complex interplay among regions forming networks. In epilepsy, these networks are disrupted causing seizures. Highly connected nodes in these networks are epilepsy surgery targets. Here, we assess whether functional connectivity (FC) using intracranial electroencephalography can quantify brain regions epileptogenicity and predict surgical outcome in children with drug resistant epilepsy (DRE). We computed FC between electrodes on different states (i.e. interictal without spikes, interictal with spikes, pre-ictal, ictal, and post-ictal) and frequency bands. We then estimated the electrodes' nodal strength. We compared nodal strength between states, inside and outside resection for good- (n = 22, Engel I) and poor-outcome (n = 9, Engel II-IV) patients, respectively, and tested their utility to predict the epileptogenic zone and outcome. We observed a hierarchical epileptogenic organization among states for nodal strength: lower FC during interictal and pre-ictal states followed by higher FC during ictal and post-ictal states (p < 0.05). We further observed higher FC inside resection (p < 0.05) for good-outcome patients on different states and bands, and no differences for poor-outcome patients. Resection of nodes with high FC was predictive of outcome (positive and negative predictive values: 47-100%). Our findings suggest that FC can discriminate epileptogenic states and predict outcome in patients with DRE.

Detecting Nonlinear Interactions in Complex Systems: Application in Financial Markets

Emerging or diminishing nonlinear interactions in the evolution of a complex system may signal a possible structural change in its underlying mechanism. This type of structural break may exist in many applications, such as in climate and finance, and standard methods for change-point detection may not be sensitive to it. In this article, we present a novel scheme for detecting structural breaks through the occurrence or vanishing of nonlinear causal relationships in a complex system. A significance resampling test was developed for the null hypothesis (H₀) of no nonlinear causal relationships using (a) an appropriate Gaussian instantaneous transform and vector autoregressive (VAR) process to generate the resampled multivariate time series consistent with H₀; (b) the modelfree Granger causality measure of partial mutual information from mixed embedding (PMIME) to estimate all causal relationships; and (c) a characteristic of the network formed by PMIME as test statistic. The significance test was applied to sliding windows on the observed multivariate time series, and the change from rejection to no-rejection of H₀, or the opposite, signaled a non-trivial change of the underlying dynamics of the observed complex system. Different network indices that capture different characteristics of the PMIME networks were used as test statistics. The test was evaluated on multiple synthetic complex and chaotic systems, as well as on linear and nonlinear stochastic systems, demonstrating that the proposed methodology is capable of detecting nonlinear causality. Furthermore, the scheme was applied to different records of financial indices regarding the global financial crisis of 2008, the two commodity crises of 2014 and 2020, the Brexit referendum of 2016, and the outbreak of COVID-19, accurately identifying the structural breaks at the identified times.

An application of dynamical directed connectivity of ictal intracranial EEG recordings in seizure onset zone localization

BACKGROUND

Identification of the seizure onset zone (SOZ) is a challenging task in epilepsy surgery. Patients with epilepsy have an altered brain network, allowing connectivity-based analyses to have a great potential in SOZ identification. We investigated a dynamical directed connectivity analysis utilizing ictal intracranial electroencephalographic (iEEG) recordings and proposed an algorithm for SOZ identification based on grouping iEEG contacts.

NEW METHODS

Granger Causality was used for directed connectivity analysis in this study. The intracranial contacts were grouped into visually detected contacts (VDCs), which were identified as SOZ by epileptologists, and non-resected contacts (NRCs). The intragroup and intergroup directed connectivity for VDCs and NRCs were calculated around seizure onset. We then proposed an algorithm for SOZ identification based on the cross-correlation of intragroup outflow and inflow of SOZ candidate contacts.

RESULTS

Our results revealed that the intragroup connectivity of VDCs (VDC→VDC) was significantly larger than the intragroup connectivity of NRCs (NRC→NRC) and the intergroup connectivity between NRCs and VDCs (NRC→VDC) around seizure onset. We found that the proposed algorithm had 90.1 % accuracy for SOZ identification in the seizure-free patients.

COMPARISON WITH EXISTING METHODS

The existing connectivity-based methods for SOZ identification often use either outflow or inflow. In this study, SOZ contacts were identified by integrating outflow and inflow based on the cross correlation between these two measures.

CONCLUSIONS

The proposed group-based dynamical connectivity analysis in this study can aid our understanding of underlying seizure network and may be used to assist in identifying the SOZ contacts before epilepsy surgery.

Relative entropy is an easy-to-use invasive electroencephalographic biomarker of the epileptogenic zone

OBJECTIVE

High-frequency oscillations are considered among the most promising interictal biomarkers of the epileptogenic zone in patients suffering from pharmacoresistant focal epilepsy. However, there is no clear definition of pathological high-frequency oscillations, and the existing detectors vary in methodology, performance, and computational costs. This study proposes relative entropy as an easy-to-use novel interictal biomarker of the epileptic tissue.

METHODS

We evaluated relative entropy and high-frequency oscillation biomarkers on intracranial electroencephalographic data from 39 patients with seizure-free postoperative outcome (Engel Ia) from three institutions. We tested their capability to localize the epileptogenic zone, defined as resected contacts located in the seizure onset zone. The performance was compared using areas under the receiver operating curves (AUROCs) and precision-recall curves. Then we tested whether a universal threshold can be used to delineate the epileptogenic zone across patients from different institutions.

RESULTS

Relative entropy in the ripple band (80-250 Hz) achieved an average AUROC of .85. The normalized high-frequency oscillation rate in the ripple band showed an identical AUROC of .85. In contrast to high-frequency oscillations, relative entropy did not require any patient-level normalization and was easy and fast to calculate due to its clear and straightforward definition. One threshold could be set across different patients and institutions, because relative entropy is independent of signal amplitude and sampling frequency.

SIGNIFICANCE

Although both relative entropy and high-frequency oscillations have a similar performance, relative entropy has significant advantages such as straightforward definition, computational speed, and universal interpatient threshold, making it an easy-to-use promising biomarker of the epileptogenic zone.

Epileptic seizure focus detection from interictal electroencephalogram: a survey

Electroencephalogram (EEG) is one of most effective clinical diagnosis modalities for the localization of epileptic focus. Most current AI solutions use this modality to analyze the EEG signals in an automated manner to identify the epileptic seizure focus. To develop AI system for identifying the epileptic focus, there are many recently-published AI solutions based on biomarkers or statistic features that utilize interictal EEGs. In this review, we survey these solutions and find that they can be divided into three main categories: (i) those that use of biomarkers in EEG signals, including high-frequency oscillation, phase-amplitude coupling, and interictal epileptiform discharges, (ii) others that utilize feature-extraction methods, and (iii) solutions based upon neural networks (an end-to-end approach). We provide a detailed description of seizure focus with clinical diagnosis methods, a summary of the public datasets that seek to reduce the research gap in epilepsy, recent novel performance evaluation criteria used to evaluate the AI systems, and guidelines on when and how to use them. This review also suggests a number of future research challenges that must be overcome in order to design more efficient computer-aided solutions to epilepsy focus detection.

Daily resting-state intracranial EEG connectivity for seizure risk forecasts

Forecasting seizure risk aims to detect proictal states in which seizures would be more likely to occur. Classical seizure prediction models are trained over long-term electroencephalographic (EEG) recordings to detect specific preictal changes for each seizure, independently of those induced by shifts in states of vigilance. A daily single measure-during a vigilance-controlled period-to estimate the risk of upcoming seizure(s) would be more convenient. Here, we evaluated whether intracranial EEG connectivity (phase-locking value), estimated from daily vigilance-controlled resting-state recordings, could allow distinguishing interictal (no seizure) from preictal (seizure within the next 24 h) states. We also assessed its relevance for daily forecasts of seizure risk using machine learning models. Connectivity in the theta band was found to provide the best prediction performances (area under the curve ≥ .7 in 80% of patients), with accurate daily and prospective probabilistic forecasts (mean Brier score and Brier skill score of .13 and .72, respectively). More efficient ambulatory clinical application could be considered using mobile EEG or chronic implanted devices.

A Feature Extraction Method for Seizure Detection Based on Multi-Site Synchronous Changes and Edge Detection Algorithm

Automatic detection of epileptic seizures is important in epilepsy control and treatment, and specific feature extraction assists in accurate detection. We developed a feature extraction method for seizure detection based on multi-site synchronous changes and an edge detection algorithm. We investigated five chronic temporal lobe epilepsy rats with 8- and 12-channel detection sites in the hippocampus and limbic system. Multi-site synchronous changes were selected as a specific feature and implemented as a seizure detection method. For preprocessing, we used magnitude-squared coherence maps and Canny edge detection algorithm to find the frequency band with the most significant change in synchronization and the important channel pairs. In detection, we used the maximal cross-correlation coefficient as an indicator of synchronization and the correlation coefficient curves' average value and standard deviation as two detection features. The method achieved high performance, with an average 96.60% detection rate, 2.63/h false alarm rate, and 1.25 s detection delay. The experimental results show that synchronization is an appropriate feature for seizure detection. The magnitude-squared coherence map can assist in selecting a specific frequency band and channel pairs to enhance the detection result. We found that individuals have a specific frequency band that reflects the most significant synchronization changes, and our method can individually adjust parameters and has good detection performance.

An Explainable Statistical Method for Seizure Prediction Using Brain Functional Connectivity from EEG

Background. Epilepsy is a group of chronic neurological disorders characterized by recurrent and abrupt seizures. The accurate prediction of seizures can reduce the burdens of this disorder. Now, existing studies use brain network features to classify patients’ preictal or interictal states, enabling seizure prediction. However, most predicting methods are based on deep learning techniques, which have weak interpretability and high computational complexity. To address these issues, in this study, we proposed a novel two-stage statistical method that is interpretable and easy to compute. Methods. We used two datasets to evaluate the performance of the proposed method, including the well-known public dataset CHB-MIT. In the first stage, we estimated the dynamic brain functional connectivity network for each epoch. Then, in the second stage, we used the derived network predictor for seizure prediction. Results. We illustrated the results of our method in seizure prediction in two datasets separately. For the FH-PKU dataset, our approach achieved an AUC value of 0.963, a prediction sensitivity of 93.1%, and a false discovery rate of 7.7%. For the CHB-MIT dataset, our approach achieved an AUC value of 0.940, a prediction sensitivity of 93.0%, and a false discovery rate of 11.1%, outperforming existing state-of-the-art methods. Significance. This study proposed an explainable statistical method, which can estimate the brain network using the scalp EEG method and use the net-work predictor to predict epileptic seizures. Availability and Implementation. R Source code is available at https://github.com/HaoChen1994/Seizure-Prediction.

High Dimensional Convolutional Neural Network for EEG Connectivity-Based Diagnosis of ADHD

Background

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults and its early detection is effective in the successful treatment of children. Electroencephalography (EEG) has been widely used for classifying ADHD and normal children. In recent years, deep learning leads to more accurate classification.

Objective

This study aims to adapt convolutional neural networks (CNNs) for classifying ADHD and normal children based on the connectivity measure of their EEG signals.

Material and Methods

In this experimental study, the dataset consisted of 61 ADHD and 60 normal children from which 13021 epochs were extracted as input for model training and evaluation. Synchronization likelihood (SL) and wavelet coherence (WC) were considered connectivity measures. The neighborhood between EEG channels was arranged in a two-dimensional matrix for better representation. Four-dimensional (4D) and six-dimensional (6D) connectivity tensors were composed as model inputs. Two architectures were developed, one 4D and 6D CNN for SL and WC-based diagnosis of ADHD, respectively.

Results

A 5-fold cross-validation was utilized to assess developed models. The average accuracy of 98.56% for 4D CNN and 98.85% for 6D CNN in epoch-based classification were obtained. In the case of subject-based classification, the accuracy was 99.17% for both models.

Conclusion

Based on the evaluation metrics of the proposed models, ADHD children can be diagnosed and ADHD and normal children can be successfully distinguished.

Diagnosis of Epilepsy with Functional Connectivity in EEG after a Suspected First Seizure

Epilepsy is regarded as a structural and functional network disorder, affecting around 50 million people worldwide. A correct disease diagnosis can lead to quicker medical action, preventing adverse effects. This paper reports the design of a classifier for epilepsy diagnosis in patients after a first ictal episode, using electroencephalogram (EEG) recordings. The dataset consists of resting-state EEG from 629 patients, of which 504 were retained for the study. The patient's cohort exists out of 291 patients with epilepsy and 213 patients with other pathologies. The data were split into two sets: 80% training set and 20% test set. The extracted features from EEG included functional connectivity measures, graph measures, band powers and brain asymmetry ratios. Feature reduction was performed, and the models were trained using Machine Learning (ML) techniques. The models' evaluation was performed with the area under the receiver operating characteristic curve (AUC). When focusing specifically on focal lesional epileptic patients, better results were obtained. This classification task was optimized using a 5-fold cross-validation, where SVM using PCA for feature reduction achieved an AUC of 0.730 ± 0.030. In the test set, the same model achieved 0.649 of AUC. The verified decrease is justified by the considerable diversity of pathologies in the cohort. An analysis of the selected features across tested models shows that functional connectivity and its graph measures have the most considerable predictive power, along with full-spectrum frequency-based features. To conclude, the proposed algorithms, with some refinement, can be of added value for doctors diagnosing epilepsy from EEG recordings after a suspected first seizure.

Variations of Resting-State EEG-Based Functional Networks in Brain Maturation From Early Childhood to Adolescence

Background and Purpose

Alterations in human brain functional networks with maturation have been explored extensively in numerous electroencephalography (EEG) and functional magnetic resonance imaging studies. It is known that the age-related changes in the functional networks occurring prior to adulthood deviate from ordinary trajectories of network-based brain maturation across the adult lifespan.

Methods

This study investigated the longitudinal evolution of resting-state EEG-based functional networks from early childhood to adolescence among 212 pediatric patients (age 12.2±3.5 years, range 4.4–17.9) in 6 frequency bands using 8 types of functional connectivity measures in the amplitude, frequency, and phase domains.

Results

Electrophysiological aspects of network-based pediatric brain maturation were characterized by increases in both functional segregation and integration up to middle adolescence. EEG oscillations in the upper alpha band reflected the age-related increases in mean node strengths and mean clustering coefficients and a decrease in the characteristic path lengths better than did those in the other frequency bands, especially for the phase-domain functional connectivity. The frequency-band-specific age-related changes in the global network metrics were influenced more by volume-conduction effects than by the domain specificity of the functional connectivity measures.

Conclusions

We believe that this is the first study to reveal EEG-based functional network properties during preadult brain maturation based on various functional connectivity measures. The findings potentially have clinical applications in the diagnosis and treatment of age-related brain disorders.

Classification of partial seizures based on functional connectivity: A MEG study with support vector machine

Temporal lobe epilepsy (TLE) is a chronic neurological disorder that is divided into two subtypes, complex partial seizures (CPS) and simple partial seizures (SPS), based on clinical phenotypes. Revealing differences among the functional networks of different types of TLE can lead to a better understanding of the symbology of epilepsy. Whereas Although most studies had focused on differences between epileptic patients and healthy controls, the neural mechanisms behind the differences in clinical representations of CPS and SPS were unclear. In the context of the era of precision, medicine makes precise classification of CPS and SPS, which is crucial. To address the above issues, we aimed to investigate the functional network differences between CPS and SPS by constructing support vector machine (SVM) models. They mainly include magnetoencephalography (MEG) data acquisition and processing, construction of functional connectivity matrix of the brain network, and the use of SVM to identify differences in the resting state functional connectivity (RSFC). The obtained results showed that classification was effective and accuracy could be up to 82.69% (training) and 81.37% (test). The differences in functional connectivity between CPS and SPS were smaller in temporal and insula. The differences between the two groups were concentrated in the parietal, occipital, frontal, and limbic systems. Loss of consciousness and behavioral disturbances in patients with CPS might be caused by abnormal functional connectivity in extratemporal regions produced by post-epileptic discharges. This study not only contributed to the understanding of the cognitive-behavioral comorbidity of epilepsy but also improved the accuracy of epilepsy classification.

Temporal and spatial dynamic propagation of electroencephalogram by combining power spectral and synchronization in childhood absence epilepsy

Objective

During the transition from normal to seizure and then to termination, electroencephalography (EEG) signals have complex changes in time-frequency-spatial characteristics. The quantitative analysis of EEG characteristics and the exploration of their dynamic propagation in this paper would help to provide new biomarkers for distinguishing between pre-ictal and inter-ictal states and to better understand the seizure mechanisms.

Methods

Thirty-three children with absence epilepsy were investigated with EEG signals. Power spectral and synchronization were combined to provide the time-frequency-spatial characteristics of EEG and analyze the spatial distribution and propagation of EEG in the brain with topographic maps. To understand the mechanism of spatial-temporal evolution, we compared inter-ictal, pre-ictal, and ictal states in EEG power spectral and synchronization network and its rhythms in each frequency band.

Results

Power, frequency, and spatial synchronization are all enhanced during the absence seizures to jointly dominate the epilepsy process. We confirmed that a rapid diffusion at the onset accompanied by the frontal region predominance exists. The EEG power rapidly bursts in 2–4 Hz through the whole brain within a few seconds after the onset. This spatiotemporal evolution is associated with spatial diffusion and brain regions interaction, with a similar pattern, increasing first and then decreasing, in both the diffusion of the EEG power and the connectivity of the brain network during the childhood absence epilepsy (CAE) seizures. Compared with the inter-ictal group, we observed increases in power of delta and theta rhythms in the pre-ictal group (P < 0.05). Meanwhile, the synchronization of delta rhythm decreased while that of alpha rhythm enhanced.

Conclusion

The initiation and propagation of CAE seizures are related to the abnormal discharge diffusion and the synchronization network. During the seizures, brain activity is completely changed with the main component delta rhythm. Furthermore, this article demonstrated for the first time that alpha inhibition, which is consistent with the brain’s feedback regulation mechanism, is caused by the enhancement of the network connection. Temporal and spatial evolution of EEG is of great significance for the transmission mechanism, clinical diagnosis and automatic detection of absence epilepsy seizures.

Ultra-high-resolution time-frequency analysis of EEG to characterise brain functional connectivity with the application in Alzheimer's disease

OBJECTIVE

This study aims to explore the potential of high-resolution brain functional connectivity based on electroencephalogram (EEG), a non-invasive low-cost technique, to be translated into a long-overdue biomarker and a diagnostic method for Alzheimer's disease (AD).

APPROACH

The paper proposes a novel ultra-high-resolution time-frequency nonlinear cross-spectrum method to construct a promising biomarker of AD pathophysiology. Specifically, using the peak frequency estimated from a Revised Hilbert-Huang Transformation cross-spectrum as a biomarker, the Support Vector Machine classifier is used to distinguish AD from healthy controls (HC).

MAIN RESULTS

With the combinations of the proposed biomarker and machine learning, we achieved a promising accuracy of 89%. The proposed method performs better than the wavelet cross-spectrum and other functional connectivity measures in the temporal or frequency domain, particularly in the Full, Delta and Alpha bands. Besides, a novel visualisation approach developed from topography is introduced to represent the brain functional connectivity, with which the difference between AD and HCs can be clearly displayed. The interconnections between posterior and other brain regions are obviously affected in AD.

SIGNIFICANCE

Those findings imply that the proposed RHHT approach could better track dynamic and nonlinear functional connectivity information, paving the way for the development of a novel diagnostic approach.

Prediction of the Responsiveness to Vagus-Nerve Stimulation in Patients with Drug-Resistant Epilepsy via Directed-Transfer-Function Analysis of Their Perioperative Scalp EEGs

This study aims to compare directed transfer function (DTF), which is an effective connectivity analysis, derived from scalp EEGs between responder and nonresponder groups implanted with vagus-nerve stimulation (VNS). Twelve patients with drug-resistant epilepsy (six responders and six nonresponders) and ten controls were recruited. A good response to VNS was defined as a reduction of ≥50% in seizure frequency compared with the presurgical baseline. DTF was calculated in five frequency bands (delta, theta, alpha, beta, and broadband) and seven grouped electrode regions (left and right frontal, temporal, parieto-occipital, and midline) in three different states (presurgical, stimulation-on, and stimulation-off states). Responders showed presurgical nodal strength close to the control group in both inflow and outflow, whereas nonresponders exhibited increased inward and outward connectivity measures. Nonresponders also had increased inward and outward connectivity measures in the various brain regions and various frequency bands assessed compared with the control group when the stimulation was on or off. Our study demonstrated that the presurgical DTF profiles of responders were different from those of nonresponders. Moreover, a presurgical normal DTF profile may predict good responsiveness to VNS.

Spatial-temporal graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram

Functional connectivity of the human brain, representing statistical dependence of information flow between cortical regions, significantly contributes to the study of the intrinsic brain network and its functional mechanism. To fully explore its potential in the early diagnosis of Alzheimer's disease (AD) using electroencephalogram (EEG) recordings, this article introduces a novel dynamical spatial-temporal graph convolutional neural network (ST-GCN) for better classification performance. Different from existing studies that are based on either topological brain function characteristics or temporal features of EEG, the proposed ST-GCN considers both the adjacency matrix of functional connectivity from multiple EEG channels and corresponding dynamics of signal EEG channel simultaneously. Different from the traditional graph convolutional neural networks, the proposed ST-GCN makes full use of the constrained spatial topology of functional connectivity and the discriminative dynamic temporal information represented by the 1D convolution. We conducted extensive experiments on the clinical EEG data set of AD patients and Healthy Controls. The results demonstrate that the proposed method achieves better classification performance (92.3%) than the state-of-the-art methods. This approach can not only help diagnose AD but also better understand the effect of normal ageing on brain network characteristics before we can accurately diagnose the condition based on resting-state EEG.

Investigation of two neural mass models for DCM-based effective connectivity inference in temporal epilepsy

BACKGROUND AND OBJECTIVE

Recently, spectral Dynamic Causal Modelling (DCM) has been used increasingly to infer effective connectivity from epileptic intracranial electroencephalographic (iEEG) signals. In this context, the Physiology-Based Model (PBM), a neural mass model, is used as a generative model. However, previous studies have highlighted out the inability of PBM to properly describe iEEG signals with specific power spectral densities (PSDs). More precisely, PSDs that have multiple peaks around β and γ rhythms (i.e. spectral characteristics at seizure onset) are concerned.

METHODS

To cope with this limitation, an alternative neural mass model, called the complete PBM (cPBM), is investigated. The spectral DCM and two recent variants are used to evaluate the relevance of cPBM over PBM.

RESULTS

The study is conducted on both simulated signals and real epileptic iEEG recordings. Our results confirm that, compared to PBM, cPBM shows (i) more ability to model the desired PSDs and (ii) lower numerical complexity whatever the method.

CONCLUSIONS

Thanks to its intrinsic and extrinsic connectivity parameters as well as the input coming into the fast inhibitory subpopulation, the cPBM provides a more expressive model of PSDs, leading to a better understanding of epileptic patterns and DCM-based effective connectivity inference.

Pediatric Seizure Prediction in Scalp EEG Using a Multi-Scale Neural Network With Dilated Convolutions

Objective: Epileptic seizure prediction based on scalp electroencephalogram (EEG) is of great significance for improving the quality of life of patients with epilepsy. In recent years, a number of studies based on deep learning methods have been proposed to address this issue and achieve excellent performance. However, most studies on epileptic seizure prediction by EEG fail to take full advantage of temporal-spatial multi-scale features of EEG signals, while EEG signals carry information in multiple temporal and spatial scales. To this end, in this study, we proposed an end-to-end framework by using a temporal-spatial multi-scale convolutional neural network with dilated convolutions for patient-specific seizure prediction. Methods: Specifically, the model divides the EEG processing pipeline into two stages: the temporal multi-scale stage and the spatial multi-scale stage. In each stage, we firstly extract the multi-scale features along the corresponding dimension. A dilated convolution block is then conducted on these features to expand our model's receptive fields further and systematically aggregate global information. Furthermore, we adopt a feature-weighted fusion strategy based on an attention mechanism to achieve better feature fusion and eliminate redundancy in the dilated convolution block. Results: The proposed model obtains an average sensitivity of 93.3%, an average false prediction rate of 0.007 per hour, and an average proportion of time-in-warning of 6.3% testing in 16 patients from the CHB-MIT dataset with the leave-one-out method. Conclusion: Our model achieves superior performance in comparison to state-of-the-art methods, providing a promising solution for EEG-based seizure prediction.

A dynamic directed transfer function for brain functional network-based feature extraction

Directed transfer function (DTF) is good at characterizing the pairwise interactions from whole brain network and has been applied in discrimination of motor imagery (MI) tasks. Considering the fact that MI electroencephalogram signals are more non-stationary in frequency domain than in time domain, and the activated intensities of α band (8–13 Hz) and β band [13–30 Hz, with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta_{1}$$\end{document}β1(13–21 Hz) and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta_{2}$$\end{document}β2(21–30 Hz) included] have considerable differences for different subjects, a dynamic DTF (DDTF) with variable model order and frequency band is proposed to construct the brain functional networks (BFNs), whose information flows and outflows are further calculated as network features and evaluated by support vector machine. Extensive experiments are conducted based on a public BCI competition dataset and a real-world dataset, the highest recognition rate achieve 100% and 86%, respectively. The experimental results suggest that DDTF can reflect the dynamic evolution of BFN, the best subject-based DDTF appears in one of four frequency sub-bands (α, β, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta_{1} ,$$\end{document}β1,\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${ }\beta_{2}$$\end{document}β2) for discrimination of MI tasks and is much more related to the current and previous states. Besides, DDTF is superior compared to granger causality-based and traditional feature extraction methods, the t-test and Kappa values show its statistical significance and high consistency as well.