The impact of EEG/MEG signal processing and modeling in the diagnostic and management of epilepsy

Mutual Supervised Fusion & Transfer Learning with Interpretable Linguistic Meaning for Social Data Analytics

Social data analytics is often taken as the most commonly used method for community discovery, product recommendations, knowledge graph, etc. In this study, social data are firstly represented in different feature spaces by using various feature extraction algorithms. Then we build a transfer learning model to leverage knowledge from multiple feature spaces. During modeling, since the assumption that the training and the testing data have the same distribution is always true, we give a theorem and its proof which asserts the necessary and sufficient condition for achieving a minimum testing error. We also theoretically demonstrate that maximizing the classification error consistency across different feature spaces can improve the classification performance. Additionally, the cluster assumption derived from semi-supervised learning is introduced to enhance knowledge transfer. Finally, a Tagaki-Sugeno-Kang (TSK) fuzzy system-based learning algorithm is proposed, which can generate interpretable fuzzy rules. Experimental results not only demonstrate the promising social data classification performance of our proposed approach but also show its interpretability which is missing in many other models.

Source imaging of deep-brain activity using the regional spatiotemporal Kalman filter

BACKGROUND AND OBJECTIVE

The human brain displays rich and complex patterns of interaction within and among brain networks that involve both cortical and subcortical brain regions. Due to the limited spatial resolution of surface electroencephalography (EEG), EEG source imaging is used to reconstruct brain sources and investigate their spatial and temporal dynamics. The majority of EEG source imaging methods fail to detect activity from subcortical brain structures. The reconstruction of subcortical sources is a challenging task because the signal from these sources is weakened and mixed with artifacts and other signals from cortical sources. In this proof-of-principle study we present a novel EEG source imaging method, the regional spatiotemporal Kalman filter (RSTKF), that can detect deep brain activity.

METHODS

The regional spatiotemporal Kalman filter (RSTKF) is a generalization of the spatiotemporal Kalman filter (STKF), which allows for the characterization of different regional dynamics in the brain. It is based on state-space modeling with spatially heterogeneous dynamical noise variances, since models with spatial and temporal homogeneity fail to describe the dynamical complexity of brain activity. First, RSTKF is tested using simulated EEG data from sources in the frontal lobe, putamen, and thalamus. After that, it is applied to non-averaged interictal epileptic spikes from a presurgical epilepsy patient with focal epileptic activity in the amygdalo-hippocampal complex. The results of RSTKF are compared to those of low-resolution brain electromagnetic tomography (LORETA) and of standard STKF.

RESULTS

Only RSTKF is successful in consistently and accurately localizing the sources in deep brain regions. Additionally, RSTKF shows improved spatial resolution compared to LORETA and STKF.

CONCLUSIONS

RSTKF is a generalization of STKF that allows for accurate, focal, and consistent localization of sources, especially in the deeper brain areas. In contrast to standard source imaging methods, RSTKF may find application in the localization of the epileptogenic zone in deeper brain structures, such as mesial frontal and temporal lobe epilepsies, especially in EEG recordings for which no reliable averaged spike shape can be obtained due to lack of the necessary number of spikes required to reach a certain signal-to-noise ratio level after averaging.

EEG Feature Selection via Stacked Deep Embedded Regression With Joint Sparsity

In the field of brain-computer interface (BCI), selecting efficient and robust features is very seductive for artificial intelligence (AI)-assisted clinical diagnosis. In this study, based on an embedded feature selection model, we construct a stacked deep structure for feature selection in a layer-by-layer manner. Its promising performance is guaranteed by the stacked generalized principle that random projections added into the original features can help us to continuously open the manifold structure existing in the original feature space in a stacked way. With such benefits, the original input feature space becomes more linearly separable. We use the epilepsy EEG data provided by the University of Bonn to evaluate our model. Based on the EEG data, we construct three classification tasks. On each task, we use different feature selection models to select features and then use two classifiers to perform classification based on the selected features. Our experimental results show that features selected by our new structure are more meaningful and helpful to the classifier hence generates better performance than benchmarking models.

IFCN-endorsed practical guidelines for clinical magnetoencephalography (MEG)

Magnetoencephalography (MEG) records weak magnetic fields outside the human head and thereby provides millisecond-accurate information about neuronal currents supporting human brain function. MEG and electroencephalography (EEG) are closely related complementary methods and should be interpreted together whenever possible. This manuscript covers the basic physical and physiological principles of MEG and discusses the main aspects of state-of-the-art MEG data analysis. We provide guidelines for best practices of patient preparation, stimulus presentation, MEG data collection and analysis, as well as for MEG interpretation in routine clinical examinations. In 2017, about 200 whole-scalp MEG devices were in operation worldwide, many of them located in clinical environments. Yet, the established clinical indications for MEG examinations remain few, mainly restricted to the diagnostics of epilepsy and to preoperative functional evaluation of neurosurgical patients. We are confident that the extensive ongoing basic MEG research indicates potential for the evaluation of neurological and psychiatric syndromes, developmental disorders, and the integrity of cortical brain networks after stroke. Basic and clinical research is, thus, paving way for new clinical applications to be identified by an increasing number of practitioners of MEG.

Seizure Prediction Using Undulated Global and Local Features

In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. These features are further used for classification of preictal/ictal and interictal EEG signals. A regularization technique is applied on the classified outputs for the reduction of false alarms and improvement of the overall prediction accuracy (PA). The experimental results confirm that the proposed method provides high PA (i.e., 95.4%) with low false positive per hour using intracranial EEG signals in different brain locations of 21 patients from a benchmark dataset. Combining global and local features enables the transition point to be determined between different types of signals with greater accuracy, resulting successful versus unsuccessful prediction of seizure. The theoretical contribution of this study may provide an opportunity for the development of a clinical device to predict forthcoming seizure in real time.

A novel dynamic update framework for epileptic seizure prediction

Epileptic seizure prediction is a difficult problem in clinical applications, and it has the potential to significantly improve the patients' daily lives whose seizures cannot be controlled by either drugs or surgery. However, most current studies of epileptic seizure prediction focus on high sensitivity and low false-positive rate only and lack the flexibility for a variety of epileptic seizures and patients' physical conditions. Therefore, a novel dynamic update framework for epileptic seizure prediction is proposed in this paper. In this framework, two basic sample pools are constructed and updated dynamically. Furthermore, the prediction model can be updated to be the most appropriate one for the prediction of seizures' arrival. Mahalanobis distance is introduced in this part to solve the problem of side information, measuring the distance between two data sets. In addition, a multichannel feature extraction method based on Hilbert-Huang transform and extreme learning machine is utilized to extract the features of a patient's preseizure state against the normal state. At last, a dynamic update epileptic seizure prediction system is built up. Simulations on Freiburg database show that the proposed system has a better performance than the one without update. The research of this paper is significantly helpful for clinical applications, especially for the exploitation of online portable devices.

Modeling Neural Activity

This paper provides an overview of different types of models for studying activity of nerve cells and their networks with a special emphasis on neural oscillations. One part describes the neuronal models based on the Hodgkin and Huxley formalism first described in the 1950s. It is discussed how further simplifications of this formalism enable mathematical analysis of the process of neural excitability. The focus of the paper’s second component is on network activity. Understanding network function is one of the important frontiers remaining in neuroscience. At present, experimental techniques can only provide global recordings or samples of the activity of the huge networks that form the nervous system. Models in neuroscience can therefore play a critical role by providing a framework for integration of necessarily incomplete datasets, thereby providing insight into the mechanisms of neural function. Network models can either explicitly contain individual network nodes that model the neurons, or they can be based on representations of compound population activity. The latter approach was pioneered by Wilson and Cowan in the 1970s. Finally I provide an overview and discuss how network models are employed in the study of neuronal network pathology such as epilepsy.

ANALYSIS OF ABSENCE SEIZURE GENERATION USING EEG SPATIAL-TEMPORAL REGULARITY MEASURES

Epileptic seizures are thought to be generated and to evolve through an underlying anomaly of synchronization in the activity of groups of neuronal populations. The related dynamic scenario of state transitions is revealed by detecting changes in the dynamical properties of Electroencephalography (EEG) signals. The recruitment procedure ending with the crisis can be explored through a spatial-temporal plot from which to extract suitable descriptors that are able to monitor and quantify the evolving synchronization level from the EEG tracings. In this paper, a spatial-temporal analysis of EEG recordings based on the concept of permutation entropy (PE) is proposed. The performance of PE are tested on a database of 24 patients affected by absence (generalized) seizures. The results achieved are compared to the dynamical behavior of the EEG of 40 healthy subjects. Being PE a feature which is dependent on two parameters, an extensive study of the sensitivity of the performance of PE with respect to the parameters' setting was carried out on scalp EEG. Once the optimal PE configuration was determined, its ability to detect the different brain states was evaluated. According to the results here presented, it seems that the widely accepted model of "jump" transition to absence seizure should be in some cases coupled (or substituted) by a gradual transition model characteristic of self-organizing networks. Indeed, it appears that the transition to the epileptic status is heralded before the preictal state, ever since the interictal stages. As a matter of fact, within the limits of the analyzed database, the frontal-temporal scalp areas appear constantly associated to PE levels higher compared to the remaining electrodes, whereas the parieto-occipital areas appear associated to lower PE values. The EEG of healthy subjects neither shows any similar dynamic behavior nor exhibits any recurrent portrait in PE topography.

Space time frequency (STF) code tensor for the characterization of the epileptic preictal stage

We evaluate the ability of multiway models to characterize the epileptic preictal period. The understanding of the characteristics of the period prior to the seizure onset is a decisive step towards the development of seizure prediction frameworks. Multiway models of EEG segments already demonstrated that hidden structures may be unveiled using tensor decomposition techniques. We propose a novel approach using a multiway model, Parallel Factor Analysis (PARAFAC), to identify spatial, temporal and spectral signatures of the preictal period. The results obtained, from a dataset of 4 patients, with a total of 30 seizures, suggest that a common structure may be involved in seizure generation. Furthermore, the spatial signature may be related to the ictal onset region and that determined frequency sub-bands may be more relevant in preictal stages.

Real-time robust signal space separation for magnetoencephalography

In this paper, we develop a robust signal space separation (rSSS) algorithm for real-time magnetoencephalography (MEG) data processing. rSSS is based on the spatial signal space separation (SSS) method and it applies robust regression to automatically detect and remove bad MEG channels so that the results of SSS are not distorted. We extend the existing robust regression algorithm via three important new contributions: 1) a low-rank solver that efficiently performs matrix operations; 2) a subspace iteration scheme that selects bad MEG channels using low-order spherical harmonic functions; and 3) a parallel computing implementation that simultaneously runs multiple tasks to further speed up numerical computation. Our experimental results based on both simulation and measurement data demonstrate that rSSS offers superior accuracy over the traditional SSS algorithm, if the MEG data contain significant outliers. Taking advantage of the proposed fast algorithm, rSSS achieves more than 75 x runtime speedup compared to a direct solver of robust regression. Even though rSSS is currently implemented with MATLAB, it already provides sufficient throughput for real-time applications.

Epileptic seizure prediction and control

Epileptic seizures are manifestations of epilepsy, a serious brain dynamical disorder second only to strokes. Of the world's approximately 50 million people with epilepsy, fully 1/3 have seizures that are not controlled by anti-convulsant medication. The field of seizure prediction, in which engineering technologies are used to decode brain signals and search for precursors of impending epileptic seizures, holds great promise to elucidate the dynamical mechanisms underlying the disorder, as well as to enable implantable devices to intervene in time to treat epilepsy. There is currently an explosion of interest in this field in academic centers and medical industry with clinical trials underway to test potential prediction and intervention methodology and devices for Food and Drug Administration (FDA) approval. This invited paper presents an overview of the application of signal processing methodologies based upon the theory of nonlinear dynamics to the problem of seizure prediction. Broader application of these developments to a variety of systems requiring monitoring, forecasting and control is a natural outgrowth of this field.