Automated Detection of Epileptic Biomarkers in Resting-State Interictal MEG Data

Estimating the likelihood of epilepsy from clinically noncontributory electroencephalograms using computational analysis: A retrospective, multisite case-control study

OBJECTIVE

This study was undertaken to validate a set of candidate biomarkers of seizure susceptibility in a retrospective, multisite case-control study, and to determine the robustness of these biomarkers derived from routinely collected electroencephalography (EEG) within a large cohort (both epilepsy and common alternative conditions such as nonepileptic attack disorder).

METHODS

The database consisted of 814 EEG recordings from 648 subjects, collected from eight National Health Service sites across the UK. Clinically noncontributory EEG recordings were identified by an experienced clinical scientist (N = 281; 152 alternative conditions, 129 epilepsy). Eight computational markers (spectral [n = 2], network-based [n = 4], and model-based [n = 2]) were calculated within each recording. Ensemble-based classifiers were developed using a two-tier cross-validation approach. We used standard regression methods to assess whether potential confounding variables (e.g., age, gender, treatment status, comorbidity) impacted model performance.

RESULTS

We found levels of balanced accuracy of 68% across the cohort with clinically noncontributory normal EEGs (sensitivity =61%, specificity =75%, positive predictive value =55%, negative predictive value =79%, diagnostic odds ratio =4.64, area under receiver operated characteristics curve =.72). Group level analysis found no evidence suggesting any of the potential confounding variables significantly impacted the overall performance.

SIGNIFICANCE

These results provide evidence that the set of biomarkers could provide additional value to clinical decision-making, providing the foundation for a decision support tool that could reduce diagnostic delay and misdiagnosis rates. Future work should therefore assess the change in diagnostic yield and time to diagnosis when utilizing these biomarkers in carefully designed prospective studies.

Resting-state brain activity distinguishes patients with generalised epilepsy from others

PURPOSE

Epilepsy is a prevalent neurological disorder characterised by repetitive seizures. It is categorised into three types: generalised epilepsy (GE), focal epilepsy (FE), and combined generalised and focal epilepsy. Correctly subtyping the epilepsy is important to select appropriate treatments. The types are mainly determined (i.e., diagnosed) by their semiologies supported by clinical examinations, such as electroencephalography and magnetoencephalography (MEG). Although these examinations are traditionally based on visual inspections of interictal epileptic discharges (IEDs), which are not always visible, alternative analyses have been anticipated. We examined if resting-state brain activities can distinguish patients with GE, which would help us to diagnose the type of epilepsy.

METHODS

The 5 min resting-state brain activities acquired using MEG were obtained retrospectively from 15 patients with GE. The cortical source of the activities was estimated at each frequency band from delta to high-frequency oscillation (HFO). These estimated activities were compared with reference datasets from 133 healthy individuals and control data from 29 patients with FE.

RESULTS

Patients with GE showed larger theta in the occipital, alpha in the left temporal, HFO in the rostral deep regions, and smaller HFO in the caudal ventral regions. Their area under the curves of the receiver operating characteristic curves was around 0.8-0.9. The distinctive pattern was not found for data from FE.

CONCLUSION

Patients with GE show distinctive resting-state brain activity, which could be a potential biomarker and used complementarily to classical analysis based on the visual inspection of IEDs.

Magnetoencephalography-based approaches to epilepsy classification

Epilepsy is a chronic central nervous system disorder characterized by recurrent seizures. Not only does epilepsy severely affect the daily life of the patient, but the risk of premature death in patients with epilepsy is three times higher than that of the normal population. Magnetoencephalography (MEG) is a non-invasive, high temporal and spatial resolution electrophysiological data that provides a valid basis for epilepsy diagnosis, and used in clinical practice to locate epileptic foci in patients with epilepsy. It has been shown that MEG helps to identify MRI-negative epilepsy, contributes to clinical decision-making in recurrent seizures after previous epilepsy surgery, that interictal MEG can provide additional localization information than scalp EEG, and complete excision of the stimulation area defined by the MEG has prognostic significance for postoperative seizure control. However, due to the complexity of the MEG signal, it is often difficult to identify subtle but critical changes in MEG through visual inspection, opening up an important area of research for biomedical engineers to investigate and implement intelligent algorithms for epilepsy recognition. At the same time, the use of manual markers requires significant time and labor costs, necessitating the development and use of computer-aided diagnosis (CAD) systems that use classifiers to automatically identify abnormal activity. In this review, we discuss in detail the results of applying various different feature extraction methods on MEG signals with different classifiers for epilepsy detection, subtype determination, and laterality classification. Finally, we also briefly look at the prospects of using MEG for epilepsy-assisted localization (spike detection, high-frequency oscillation detection) due to the unique advantages of MEG for functional area localization in epilepsy, and discuss the limitation of current research status and suggestions for future research. Overall, it is hoped that our review will facilitate the reader to quickly gain a general understanding of the problem of MEG-based epilepsy classification and provide ideas and directions for subsequent research.

Resting state functional connectivity demonstrates increased segregation in bilateral temporal lobe epilepsy

OBJECTIVE

Temporal lobe epilepsy (TLE) is the most common type of focal epilepsy. An increasingly identified subset of patients with TLE consists of those who show bilaterally independent temporal lobe seizures. The purpose of this study was to leverage network neuroscience to better understand the interictal whole brain network of bilateral TLE (BiTLE).

METHODS

In this study, using a multicenter resting state functional magnetic resonance imaging (rs-fMRI) data set, we constructed whole-brain functional networks of 19 patients with BiTLE, and compared them to those of 75 patients with unilateral TLE (UTLE). We quantified resting-state, whole-brain topological properties using metrics derived from network theory, including clustering coefficient, global efficiency, participation coefficient, and modularity. For each metric, we computed an average across all brain regions, and iterated this process across network densities. Curves of network density vs each network metric were compared between groups. Finally, we derived a combined metric, which we term the "integration-segregation axis," by combining whole-brain average clustering coefficient and global efficiency curves, and applying principal component analysis (PCA)-based dimensionality reduction.

RESULTS

Compared to UTLE, BiTLE had decreased global efficiency (p = .031), and decreased whole brain average participation coefficient across a range of network densities (p = .019). Modularity maximization yielded a larger number of smaller communities in BiTLE than in UTLE (p = .020). Differences in network properties separate BiTLE and UTLE along the integration-segregation axis, with regions within the axis having a specificity of up to 0.87 for BiTLE. Along the integration-segregation axis, UTLE patients with poor surgical outcomes were distributed in the same regions as BiTLE, and network metrics confirmed similar patterns of increased segregation in both BiTLE and poor outcome UTLE.

SIGNIFICANCE

Increased interictal whole-brain network segregation, as measured by rs-fMRI, is specific to BiTLE, as well as poor surgical outcome UTLE, and may assist in non-invasively identifying this patient population prior to intracranial electroencephalography or device implantation.

Altered neuromagnetic activity in default mode network in childhood absence epilepsy

Purpose

The electrophysiological characterization of resting state oscillatory functional connectivity within the default mode network (DMN) during interictal periods in childhood absence epilepsy (CAE) remains unclear. Using magnetoencephalographic (MEG) recordings, this study investigated how the connectivity within the DMN was altered in CAE.

Methods

Using a cross-sectional design, we analyzed MEG data from 33 children newly diagnosed with CAE and 26 controls matched for age and sex. The spectral power and functional connectivity of the DMN were estimated using minimum norm estimation combined with the Welch technique and corrected amplitude envelope correlation.

Results

Default mode network showed stronger activation in the delta band during the ictal period, however, the relative spectral power in other bands was significantly lower than that in the interictal period (pcorrected < 0.05 for DMN regions, except bilateral medial frontal cortex, left medial temporal lobe, left posterior cingulate cortex in the theta band, and the bilateral precuneus in the alpha band). It should be noted that the significant power peak in the alpha band was lost compared with the interictal data. Compared with controls, the interictal relative spectral power of DMN regions (except bilateral precuneus) in CAE patients was significantly increased in the delta band (pcorrected < 0.01), whereas the values of all DMN regions in the beta-gamma 2 band were significantly decreased (pcorrected < 0.01). In the higher frequency band (alpha-gamma1), especially in the beta and gamma1 band, the ictal node strength of DMN regions except the left precuneus was significantly higher than that in the interictal periods (pcorrected < 0.01), and the node strength of the right inferior parietal lobe increased most significantly in the beta band (Ictal: 3.8712 vs. Interictal: 0.7503, pcorrected < 0.01). Compared with the controls, the interictal node strength of DMN increased in all frequency bands, especially the right medial frontal cortex in the beta band (Controls: 0.1510 vs. Interictal: 3.527, pcorrected < 0.01). Comparing relative node strength between groups, the right precuneus in CAE children decreased significantly (β: Controls: 0.1009 vs. Interictal: 0.0475; γ 1: Controls:0.1149 vs. Interictal:0.0587, pcorrected < 0.01) such that it was no longer the central hub.

Conclusion

These findings indicated DMN abnormalities in CAE patients, even in interictal periods without interictal epileptic discharges. Abnormal functional connectivity in CAE may reflect abnormal anatomo-functional architectural integration in DMN, as a result of cognitive mental impairment and unconsciousness during absence seizure. Future studies are needed to examine if the altered functional connectivity can be used as a biomarker for treatment responses, cognitive dysfunction, and prognosis in CAE patients.

Data Augmentation Effects on Highly Imbalanced EEG Datasets for Automatic Detection of Photoparoxysmal Responses

Photosensitivity is a neurological disorder in which a person's brain produces epileptic discharges, known as Photoparoxysmal Responses (PPRs), when it receives certain visual stimuli. The current standardized diagnosis process used in hospitals consists of submitting the subject to the Intermittent Photic Stimulation process and attempting to trigger these phenomena. The brain activity is measured by an Electroencephalogram (EEG), and the clinical specialists manually look for the PPRs that were provoked during the session. Due to the nature of this disorder, long EEG recordings may contain very few PPR segments, meaning that a highly imbalanced dataset is available. To tackle this problem, this research focused on applying Data Augmentation (DA) to create synthetic PPR segments from the real ones, improving the balance of the dataset and, thus, the global performance of the Machine Learning techniques applied for automatic PPR detection. K-Nearest Neighbors and a One-Hidden-Dense-Layer Neural Network were employed to evaluate the performance of this DA stage. The results showed that DA is able to improve the models, making them more robust and more able to generalize. A comparison with the results obtained from a previous experiment also showed a performance improvement of around 20% for the Accuracy and Specificity measurements without Sensitivity suffering any losses. This project is currently being carried out with subjects at Burgos University Hospital, Spain.

EEG biomarker candidates for the identification of epilepsy

Electroencephalography (EEG) is one of the main pillars used for the diagnosis and study of epilepsy, readily employed after a possible first seizure has occurred. The most established biomarker of epilepsy, in case seizures are not recorded, are interictal epileptiform discharges (IEDs). In clinical practice, however, IEDs are not always present and the EEG may appear completely normal despite an underlying epileptic disorder, often leading to difficulties in the diagnosis of the disease. Thus, finding other biomarkers that reliably predict whether an individual suffers from epilepsy even in the absence of evident epileptic activity would be extremely helpful, since they could allow shortening the period of diagnostic uncertainty and consequently decreasing the risk of seizure. To date only a few EEG features other than IEDs seem to be promising candidates able to distinguish between epilepsy, i.e. > 60 % risk of recurrent seizures, or other (pathological) conditions. The aim of this narrative review is to provide an overview of the EEG-based biomarker candidates for epilepsy and the techniques employed for their identification.

Abnormal phase-amplitude coupling characterizes the interictal state in epilepsy

OBJECTIVE

 Diagnosing epilepsy still requires visual interpretation of electroencephalography and magnetoencephalography (MEG) by specialists, which prevents quantification and standardization of diagnosis. Previous studies proposed automated diagnosis by combining various features from electroencephalography and MEG, such as relative power (Power) and functional connectivity. However, the usefulness of interictal phase-amplitude coupling (PAC) in diagnosing epilepsy is still unknown. We hypothesized that resting-state PAC would be different for patients with epilepsy in the interictal state and for healthy participants such that it would improve discrimination between the groups.

METHODS

 We obtained resting-state MEG and magnetic resonance imaging in 90 patients with epilepsy during their preoperative evaluation and in 90 healthy participants. We used the cortical currents estimated from MEG and magnetic resonance imaging to calculate Power in the δ (1-3 Hz), θ (4-7 Hz), α (8-13 Hz), β (13-30 Hz), low γ (35-55 Hz), and high γ (65-90 Hz) bands and functional connectivity in the θ band. PAC was evaluated using the synchronization index (SI) for eight frequency band pairs: the phases of δ, θ, α, and β and the amplitudes of low and high γ. First, we compared the mean SI values for the patients with epilepsy and the healthy participants. Then, using features such as PAC, Power, functional connectivity, and features extracted by deep learning individually or combined, we tested whether PAC improves discrimination accuracy for the two groups.

RESULTS

 The mean SI values were significantly different for the patients with epilepsy and the healthy participants. The SI value difference was highest for θ/low γ in the temporal lobe. Discrimination accuracy was the highest, at 90%, using the combination of PAC and deep learning.

SIGNIFICANCE

 Abnormal PAC characterized the patients with epilepsy in the interictal state compared with the healthy participants, potentially improving the discrimination of epilepsy.

Virtual reality and machine learning in the automatic photoparoxysmal response detection

Photosensitivity, in relation to epilepsy, is a genetically determined condition in which patients have epileptic seizures of different severity provoked by visual stimuli. It can be diagnosed by detecting epileptiform discharges in their electroencephalogram (EEG), known as photoparoxysmal responses (PPR). The most accepted PPR detection method—a manual method—considered as the standard one, consists in submitting the subject to intermittent photic stimulation (IPS), i.e. a flashing light stimulation at increasing and decreasing flickering frequencies in a hospital room under controlled ambient conditions, while at the same time recording her/his brain response by means of EEG signals. This research focuses on introducing virtual reality (VR) in this context, adding, to the conventional infrastructure a more flexible one that can be programmed and that will allow developing a much wider and richer set of experiments in order to detect neurological illnesses, and to study subjects’ behaviours automatically. The loop includes the subject, the VR device, the EEG infrastructure and a computer to analyse and monitor the EEG signal and, in some cases, provide feedback to the VR. As will be shown, AI modelling will be needed in the automatic detection of PPR, but it would also be used in extending the functionality of this system with more advanced features. This system is currently in study with subjects at Burgos University Hospital, Spain.

A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls

Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects.

Comparison of Resampling Techniques for Imbalanced Datasets in Machine Learning: Application to Epileptogenic Zone Localization From Interictal Intracranial EEG Recordings in Patients With Focal Epilepsy

Aim: In neuroscience research, data are quite often characterized by an imbalanced distribution between the majority and minority classes, an issue that can limit or even worsen the prediction performance of machine learning methods. Different resampling procedures have been developed to face this problem and a lot of work has been done in comparing their effectiveness in different scenarios. Notably, the robustness of such techniques has been tested among a wide variety of different datasets, without considering the performance of each specific dataset. In this study, we compare the performances of different resampling procedures for the imbalanced domain in stereo-electroencephalography (SEEG) recordings of the patients with focal epilepsies who underwent surgery.

Methods: We considered data obtained by network analysis of interictal SEEG recorded from 10 patients with drug-resistant focal epilepsies, for a supervised classification problem aimed at distinguishing between the epileptogenic and non-epileptogenic brain regions in interictal conditions. We investigated the effectiveness of five oversampling and five undersampling procedures, using 10 different machine learning classifiers. Moreover, six specific ensemble methods for the imbalanced domain were also tested. To compare the performances, Area under the ROC curve (AUC), F-measure, Geometric Mean, and Balanced Accuracy were considered.

Results: Both the resampling procedures showed improved performances with respect to the original dataset. The oversampling procedure was found to be more sensitive to the type of classification method employed, with Adaptive Synthetic Sampling (ADASYN) exhibiting the best performances. All the undersampling approaches were more robust than the oversampling among the different classifiers, with Random Undersampling (RUS) exhibiting the best performance despite being the simplest and most basic classification method.

Conclusions: The application of machine learning techniques that take into consideration the balance of features by resampling is beneficial and leads to more accurate localization of the epileptogenic zone from interictal periods. In addition, our results highlight the importance of the type of classification method that must be used together with the resampling to maximize the benefit to the outcome.

Identifying juvenile myoclonic epilepsy via diffusion tensor imaging using machine learning analysis

The aim of this study was to evaluate the feasibility of using a machine learning approach based on diffusion tensor imaging (DTI) to identify patients with juvenile myoclonic epilepsy. We analyzed the usefulness of combining conventional DTI measures and structural connectomic profiles. This retrospective study was conducted at a tertiary hospital. We enrolled 55 patients with juvenile myoclonic epilepsy. All of the subjects underwent DTI from January 2017 to March 2020. We also enrolled 58 healthy subjects as a normal control group. We extracted conventional DTI measures and structural connectomic DTI profiles. We employed the support vector machines (SVM) algorithm to classify patients with juvenile myoclonic epilepsy and healthy subjects based on the conventional DTI measures and structural connectomic profiles. The SVM classifier based on conventional DTI measures had an accuracy of 68.1% and an area under the curve (AUC) of 0.682. Another SVM classifier based on the structural connectomic profiles demonstrated an accuracy of 72.7% and an AUC of 0.727. The SVM classifier based on combining the conventional DTI measures and structural connectomic profiles had an accuracy of 81.8% and an AUC of 0.818. DTI using machine learning is useful for classifying patients with juvenile myoclonic epilepsy and healthy subjects. Combining both the conventional DTI measures and structural connectomic profiles results in a better classification performance than using conventional DTI measures or the structural connectomic profiles alone to identify juvenile myoclonic epilepsy.

Identification of focal epilepsy by diffusion tensor imaging using machine learning

OBJECTIVE

The aim of this study was to evaluate the feasibility of machine learning based on diffusion tensor imaging (DTI) measures to distinguish patients with focal epilepsy versus healthy controls and antiseizure medication (ASM) responsiveness.

METHODS

This was a retrospective study performed at a tertiary hospital. We enrolled 456 patients with focal epilepsy, who underwent DTI and were taking ASMs. We enrolled 100 healthy subjects as a control. We obtained the conventional DTI measures and structural connectomic profiles from the DTI.

RESULTS

The support vector machine (SVM) classifier based on the conventional DTI measures revealed an accuracy of 76.5% and an area under curve (AUC) of 0.604 (95% Confidence interval (CI), 0.506-0.695). Another SVM classifier combined with structural connectomic profiles demonstrated an accuracy of 82.8% and an AUC of 0.701 (95% CI, 0.606-0.784). Of the 456 patients with epilepsy, 242 patients were ASM good responders, whereas 214 patients were ASM poor responders. In the classification of the ASM responders, an SVM classifier based on the conventional DTI measures revealed an accuracy of 54.9% and an AUC of 0.551 (95% CI, 0.443-0.655). Another SVM classifier combined with structural connectomic profiles demonstrated an accuracy of 59.3% and an AUC of 0.594 (95% CI, 0.485-0.695).

CONCLUSION

DTI using a machine learning is useful for differentiating patients with focal epilepsy from healthy controls, but it cannot classify ASM responsiveness. Combining structural connectomic profiles results in a better classification performance than the use of conventional DTI measures alone for identifying focal epilepsy and ASM responsiveness.

A computational biomarker of juvenile myoclonic epilepsy from resting-state MEG

•

Computational modelling is combined with MEG to differentiate people with juvenile myoclonic epilepsy from healthy controls.

•

Brain network ictogenicity (BNI) was found higher in people with juvenile myoclonic epilepsy relative to healthy controls.

•

BNI’s classification accuracy in our cohort was 73%.

Objective

For people with idiopathic generalized epilepsy, functional networks derived from their resting-state scalp electrophysiological recordings have shown an inherent higher propensity to generate seizures than those from healthy controls when assessed using the concept of brain network ictogenicity (BNI). Herein we tested whether the BNI framework is applicable to resting-state magnetoencephalography (MEG) from people with juvenile myoclonic epilepsy (JME).

Methods

The BNI framework consists in deriving a functional network from apparently normal brain activity, placing a mathematical model of ictogenicity into the network and then computing how often such network generates seizures in silico. We considered data from 26 people with JME and 26 healthy controls.

Results

We found that resting-state MEG functional networks from people with JME are characterized by a higher propensity to generate seizures (i.e., higher BNI) than those from healthy controls. We found a classification accuracy of 73%.

Conclusions

The BNI framework is applicable to MEG and was capable of differentiating people with epilepsy from healthy controls.

Significance

The BNI framework may be applied to resting-state MEG to aid in epilepsy diagnosis.

A Feature Tensor-Based Epileptic Detection Model Based on Improved Edge Removal Approach for Directed Brain Networks

Electroencephalograph (EEG) plays a significant role in the diagnostics process of epilepsy, but the detection rate is unsatisfactory when the length of interictal EEG signals is relatively short. Although the deliberate attacking theories for undirected brain network based on node removal method can extract potential network features, the node removal method fails to sufficiently consider the directionality of brain electrical activities. To solve the problems above, this study proposes a feature tensor-based epileptic detection method of directed brain networks. First, a directed functional brain network is constructed by calculating the transfer entropy of EEG signals between different electrodes. Second, the edge removal method is used to imitate the disruptions of brain connectivity, which may be related to the disorder of brain diseases, to obtain a sequence of residual networks. After that, topological features of these residual networks are extracted based on graph theory for constructing a five-way feature tensor. To exploit the inherent interactions among multiple modes of the feature tensor, this study uses the Tucker decomposition method to get a core tensor which is finally reshaped into a vector and input into the support vectors machine (SVM) classifier. Experiment results suggest that the proposed method has better epileptic screening performance for short-term interictal EEG data.

Machine learning applications in epilepsy

Machine learning leverages statistical and computer science principles to develop algorithms capable of improving performance through interpretation of data rather than through explicit instructions. Alongside widespread use in image recognition, language processing, and data mining, machine learning techniques have received increasing attention in medical applications, ranging from automated imaging analysis to disease forecasting. This review examines the parallel progress made in epilepsy, highlighting applications in automated seizure detection from electroencephalography (EEG), video, and kinetic data, automated imaging analysis and pre-surgical planning, prediction of medication response, and prediction of medical and surgical outcomes using a wide variety of data sources. A brief overview of commonly used machine learning approaches, as well as challenges in further application of machine learning techniques in epilepsy, is also presented. With increasing computational capabilities, availability of effective machine learning algorithms, and accumulation of larger datasets, clinicians and researchers will increasingly benefit from familiarity with these techniques and the significant progress already made in their application in epilepsy.

Brain Functional Connectivity Through Phase Coupling of Neuronal Oscillations: A Perspective From Magnetoencephalography

Magnetoencephalography has gained an increasing importance in systems neuroscience thanks to the possibility it offers of unraveling brain networks at time-scales relevant to behavior, i.e., frequencies in the 1-100 Hz range, with sufficient spatial resolution. In the first part of this review, we describe, in a unified mathematical framework, a large set of metrics used to estimate MEG functional connectivity at the same or at different frequencies. The different metrics are presented according to their characteristics: same-frequency or cross-frequency, univariate or multivariate, directed or undirected. We focus on phase coupling metrics given that phase coupling of neuronal oscillations is a putative mechanism for inter-areal communication, and that MEG is an ideal tool to non-invasively detect such coupling. In the second part of this review, we present examples of the use of specific phase methods on real MEG data in the context of resting state, visuospatial attention and working memory. Overall, the results of the studies provide evidence for frequency specific and/or cross-frequency brain circuits which partially overlap with brain networks as identified by hemodynamic-based imaging techniques, such as functional Magnetic Resonance (fMRI). Additionally, the relation of these functional brain circuits to anatomy and to behavior highlights the usefulness of MEG phase coupling in systems neuroscience studies. In conclusion, we believe that the field of MEG functional connectivity has made substantial steps forward in the recent years and is now ready for bringing the study of brain networks to a more mechanistic understanding.

Background EEG Connectivity Captures the Time-Course of Epileptogenesis in a Mouse Model of Epilepsy

Large-scale brain networks are increasingly recognized as important for the generation of seizures in epilepsy. However, how a network evolves from a healthy state through the process of epileptogenesis remains unclear. To address this question, here, we study longitudinal epicranial background EEG recordings (30 electrodes, EEG free from epileptiform activity) of a mouse model of mesial temporal lobe epilepsy. We analyze functional connectivity networks and observe that over the time course of epileptogenesis the networks become increasingly asymmetric. Furthermore, computational modelling reveals that a set of nodes, located outside of the region of initial insult, emerges as particularly important for the network dynamics. These findings are consistent with experimental observations, thus demonstrating that ictogenic mechanisms can be revealed on the EEG, that computational models can be used to monitor unfolding epileptogenesis and that both the primary focus and epileptic network play a role in epileptogenesis.

The blessing of Dimensionality: Feature Selection outperforms functional connectivity-based feature transformation to classify ADHD subjects from EEG patterns of phase synchronisation

Functional connectivity (FC) characterizes brain activity from a multivariate set of N brain signals by means of an NxN matrix A, whose elements estimate the dependence within each possible pair of signals. Such matrix can be used as a feature vector for (un)supervised subject classification. Yet if N is large, A is highly dimensional. Little is known on the effect that different strategies to reduce its dimensionality may have on its classification ability. Here, we apply different machine learning algorithms to classify 33 children (age [6-14 years]) into two groups (healthy controls and Attention Deficit Hyperactivity Disorder patients) using EEG FC patterns obtained from two phase synchronisation indices. We found that the classification is highly successful (around 95%) if the whole matrix A is taken into account, and the relevant features are selected using machine learning methods. However, if FC algorithms are applied instead to transform A into a lower dimensionality matrix, the classification rate drops to less than 80%. We conclude that, for the purpose of pattern classification, the relevant features should be selected among the elements of A by using appropriate machine learning algorithms.

Predicting seizure outcome of vagus nerve stimulation using MEG-based network topology

Vagus nerve stimulation (VNS) is a low-risk surgical option for patients with drug resistant epilepsy, although it is impossible to predict which patients may respond to VNS treatment. Resting-state magnetoencephalography (rs-MEG) connectivity analysis has been increasingly utilized to investigate the impact of epilepsy on brain networks and identify alteration of these networks after different treatments; however, there is no study to date utilizing this modality to predict the efficacy of VNS treatment. We investigated whether the rs-MEG network topology before VNS implantation can be used to predict efficacy of VNS treatment. Twenty-three patients with epilepsy who had MEG before VNS implantation were included in this study. We also included 89 healthy control subjects from the Human Connectome Project. Using the phase-locking value in the theta, alpha, and beta frequency bands as a measure of rs-MEG functional connectivity, we calculated three global graph measures: modularity, transitivity, and characteristic path length (CPL). Our results revealed that the rs-MEG graph measures were significantly heritable and had an overall good test-retest reliability, and thus these measures may be used as potential biomarkers of the network topology. We found that the modularity and transitivity in VNS responders were significantly larger and smaller, respectively, than those observed in VNS non-responders. We also observed that the modularity and transitivity in three frequency bands and CPL in delta and beta bands were significantly different in controls than those found in responders or non-responders, although the values of the graph measures in controls were closer to those of responders than non-responders. We used the modularity and transitivity as input features of a naïve Bayes classifier, and achieved an accuracy of 87% in classification of non-responders, responders, and controls. The results of this study revealed that MEG-based graph measures are reliable biomarkers, and that these measures may be used to predict seizure outcome of VNS treatment.