Discrimination of Tourette Syndrome Based on the Spatial Patterns of the Resting-State EEG Network.

Tourette syndrome (TS) is a neuropsychiatric disorder with childhood onset characterized by chronic motor and vocal tics; however, the current diagnosis of TS patients is subjective, as it is mainly assessed based on the parents' description alongside specific evaluations. The early and accurate diagnosis of TS based on its potential symptoms in children would be of benefit in their future therapy, but reliable diagnoses are difficult due to the lack of objective knowledge of the etiology and pathogenesis of TS. In this study, resting-state electroencephalograms were first collected from 36 patients and 21 healthy controls (HCs); the corresponding resting-state functional networks were then constructed, and the potential differences in network topology between the two groups were extracted by using the topology of the spatial pattern of the network (SPN). Compared to the HCs, the TS patients exhibited decreased frontotemporal/occipital/parietal connectivity. When classifying the two groups, compared to the network properties, the derived SPN features achieved a much higher accuracy of 92.31%. The intrinsic long-range connectivity between the frontal and the temporal/occipital/parietal lobes was damaged in the patient group, and this dysfunctional network pattern might serve as a reliable biomarker to differentiate TS patients from HCs as well as to assess the severity of tic symptoms.

Prediction of mild parkinsonism revealed by neural oscillatory changes and machine learning.

Neural oscillatory changes within and across different frequency bands are thought to underlie motor dysfunction in Parkinson's disease (PD) and may serve as biomarkers for closed-loop deep brain stimulation (DBS) approaches. Here, we used neural oscillatory signals derived from chronically implanted cortical and subcortical electrode arrays as features to train machine learning algorithms to discriminate between naive and mild PD states in a nonhuman primate model. Local field potential (LFP) data were collected over several months from a 12-channel subdural electrocorticography (ECoG) grid and a 6-channel custom array implanted in the subthalamic nucleus (STN). Relative to the naive state, the PD state showed elevated primary motor cortex (M1) and STN power in the beta, high gamma, and high-frequency oscillation (HFO) bands and decreased power in the delta band. Theta power was found to be decreased in STN but not M1. In the PD state there was elevated beta-HFO phase-amplitude coupling (PAC) in the STN. We applied machine learning with support vector machines with radial basis function (SVM-RBF) kernel and k-nearest neighbors (KNN) classifiers trained by features related to power and PAC changes to discriminate between the naive and mild states. Our results show that the most predictive feature of parkinsonism in the STN was high beta (∼86% accuracy), whereas it was HFO in M1 (∼98% accuracy). A feature fusion approach outperformed every individual feature, particularly in the M1, where ∼98% accuracy was achieved with both classifiers. Overall, our data demonstrate the ability to use various frequency band power to classify the clinical state and are also beneficial in developing closed-loop DBS therapeutic approaches.NEW & NOTEWORTHY Neurophysiological biomarkers that correlate with motor symptoms or disease severity are vital to improve our understanding of the pathophysiology in Parkinson's disease (PD) and for the development of more effective treatments, including deep brain stimulation (DBS). This work provides direct insight into the application of these biomarkers in training classifiers to discriminate between brain states, which is a first step toward developing closed-loop DBS systems.

L1-norm based time-varying brain neural network and its application to dynamic analysis for motor imagery.

Objective.Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interface offers a promising way to improve the efficiency of motor rehabilitation and motor skill learning. In recent years, the power of dynamic network analysis for MI classification has been proved. In fact, its usability mainly depends on the accurate estimation of brain connection. However, traditional dynamic network estimation strategies such as adaptive directed transfer function (ADTF) are designed in the L2-norm. Usually, they estimate a series of pseudo connections caused by outliers, which results in biased features and further limits its online application. Thus, how to accurately infer dynamic causal relationship under outlier influence is urgent.Approach.In this work, we proposed a novel ADTF, which solves the dynamic system in the L1-norm space (L1-ADTF), so as to restrict the outlier influence. To enhance its convergence, we designed an iteration strategy with the alternating direction method of multipliers, which could be used for the solution of the dynamic state-space model restricted in the L1-norm space. Furthermore, we compared L1-ADTF to traditional ADTF and its dual extension across both simulation and real EEG experiments.Main results.A quantitative comparison between L1-ADTF and other ADTFs in simulation studies demonstrates that fewer bias errors and more desirable dynamic state transformation patterns can be captured by the L1-ADTF. Application to real MI EEG datasets seriously noised by ocular artifacts also reveals the efficiency of the proposed L1-ADTF approach to extract the time-varying brain neural network patterns, even when more complex noises are involved.Significance.The L1-ADTF may not only be capable of tracking time-varying brain network state drifts robustly but may also be useful in solving a wide range of dynamic systems such as trajectory tracking problems and dynamic neural networks.

Consistent Changes in Cortico-Subthalamic Directed Connectivity Are Associated With the Induction of Parkinsonism in a Chronically Recorded Non-human Primate Model.

Parkinson's disease is a neurological disease with cardinal motor signs including bradykinesia and tremor. Although beta-band hypersynchrony in the cortico-basal ganglia network is thought to contribute to disease manifestation, the resulting effects on network connectivity are unclear. We examined local field potentials from a non-human primate across the naïve, mild, and moderate disease states (model was asymmetric, left-hemispheric dominant) and probed power spectral density as well as cortico-cortical and cortico-subthalamic connectivity using both coherence and Granger causality, which measure undirected and directed effective connectivity, respectively. Our network included the left subthalamic nucleus (L-STN), bilateral primary motor cortices (L-M1, R-M1), and bilateral premotor cortices (L-PMC, R-PMC). Results showed two distinct peaks (Peak A at 5-20 Hz, Peak B at 25-45 Hz) across all analyses. Power and coherence analyses showed widespread increases in power and connectivity in both the Peak A and Peak B bands with disease progression. For Granger causality, increases in Peak B connectivity and decreases in Peak A connectivity were associated with the disease. Induction of mild disease was associated with several changes in connectivity: (1) the cortico-subthalamic connectivity in the descending direction (L-PMC to L-STN) decreased in the Peak A range while the reciprocal, ascending connectivity (L-STN to L-PMC) increased in the Peak B range; this may play a role in generating beta-band hypersynchrony in the cortex, (2) both L-M1 to L-PMC and R-M1 to R-PMC causalities increased, which may either be compensatory or a pathologic effect of disease, and (3) a decrease in connectivity occurred from the R-PMC to R-M1. The only significant change seen between mild and moderate disease was increased right cortical connectivity, which may reflect compensation for the left-hemispheric dominant moderate disease state.

A Long Short-Term Memory Network for Sparse Spatiotemporal EEG Source Imaging.

EEG inverse problem is underdetermined, which poses a long standing challenge in Neuroimaging. The combination of source-imaging and analysis of cortical directional networks enables us to noninvasively explore the underlying neural processes. However, existing EEG source imaging approaches mainly focus on performing the direct inverse operation for source estimation, which will be inevitably influenced by noise and the strategy used to find the inverse solution. Here, we develop a new source imaging technique, Deep Brain Neural Network (DeepBraiNNet), for robust sparse spatiotemporal EEG source estimation. In DeepBraiNNet, considering that Recurrent Neural Network (RNN) are usually "deep" in temporal dimension and thus suitable for time sequence modelling, the RNN with Long Short-Term Memory (LSTM) is utilized to approximate the inverse operation for the lead field matrix instead of performing the direct inverse operation, which avoids the possible effect of the direct inverse operation on the underdetermined lead field matrix prone to be influenced by noise. Simulations on various source patterns and noise conditions confirmed that the proposed approach could actually recover the spatiotemporal sources well, outperforming existing state of-the-art methods. DeepBraiNNet also estimated sparse MI related activation patterns when it was applied to a real Motor Imagery dataset, consistent with other findings based on EEG and fMRI. Based on the spatiotemporal sources estimated from DeepBraiNNet, we constructed MI related cortical neural networks, which clearly exhibited strong contralateral network patterns for the two MI tasks. Consequently, DeepBraiNNet may provide an alternative way different from the conventional approaches for spatiotemporal EEG source imaging.

Directed EEG neural network analysis by LAPPS (p≤1) Penalized sparse Granger approach.

The conventional multivariate Granger Analysis (GA) of directed interactions has been widely applied in brain network construction based on EEG recordings as well as fMRI. Nevertheless, EEG is usually inevitably contaminated by strong noise, which may cause network distortion due to the L2-norm used in GAs for directed network recovery. The Lp (p ≤1) norm has been shown to be more robust to outliers as compared to LASSO and L2-GAs. Motivated to construct the sparse brain networks under strong noise condition, we hereby introduce a new approach for GA analysis, termed LAPPS (Least Absolute LP (0

Measuring the Non-linear Directed Information Flow in Schizophrenia by Multivariate Transfer Entropy.

People living with schizophrenia (SCZ) experience severe brain network deterioration. The brain is constantly fizzling with non-linear causal activities measured by electroencephalogram (EEG) and despite the variety of effective connectivity methods, only few approaches can quantify the direct non-linear causal interactions. To circumvent this problem, we are motivated to quantitatively measure the effective connectivity by multivariate transfer entropy (MTE) which has been demonstrated to be able to capture both linear and non-linear causal relationships effectively. In this work, we propose to construct the EEG effective network by MTE and further compare its performance with the Granger causal analysis (GCA) and Bivariate transfer entropy (BVTE). The simulation results quantitatively show that MTE outperformed GCA and BVTE under varied signal-to-noise conditions, edges recovered, sensitivity, and specificity. Moreover, its applications to the P300 task EEG of healthy controls (HC) and SCZ patients further clearly show the deteriorated network interactions of SCZ, compared to that of the HC. The MTE provides a novel tool to potentially deepen our knowledge of the brain network deterioration of the SCZ.

Sparse EEG Source Localization Using LAPPS: Least Absolute l-P (0 < p < 1) Penalized Solution.

OBJECTIVE: The electroencephalographic (EEG) inverse problem is ill-posed owing to the electromagnetism Helmholtz theorem and since there are fewer observations than the unknown variables. Apart from the strong background activities (ongoing EEG), evoked EEG is also inevitably contaminated by strong outliers caused by head movements or ocular movements during recordings. METHODS: Considering the sparse activations during high cognitive processing, we propose a novel robust EEG source imaging algorithm, LAPPS (Least Absolute -P (0 < p < 1) Penalized Solution), which employs the -loss for the residual error to alleviate the effect of outliers and another -penalty norm (p=0.5) to obtain sparse sources while suppressing Gaussian noise in EEG recordings. The resulting optimization problem is solved using a modified ADMM algorithm. RESULTS: Simulation study was performed to recover sparse signals of randomly selected sources using LAPPS and various methods commonly used for EEG source imaging including WMNE, -norm, sLORETA and FOCUSS solution. The simulation comparison quantitatively demonstrates that LAPPS obtained the best performances in all the conducted simulations for various dipoles configurations under various SNRs on a realistic head model. Moreover, in the localization of brain neural generators in a real visual oddball experiment, LAPPS obtained sparse activations consistent with previous findings revealed by EEG and fMRI. CONCLUSION: This study demonstrates a potentially useful sparse method for EEG source imaging, creating a platform for investigating the brain neural generators. SIGNIFICANCE: This method alleviates the effect of noise and recovers sparse sources while maintaining a low computational complexity due to the cheap matrix-vector multiplication.