Real-time EEG Source-mapping Toolbox (REST): Online ICA and source localization

MOVING: A Multi-Modal Dataset of EEG Signals and Virtual Glove Hand Tracking

Brain-computer interfaces (BCIs) are pivotal in translating neural activities into control commands for external assistive devices. Non-invasive techniques like electroencephalography (EEG) offer a balance of sensitivity and spatial-temporal resolution for capturing brain signals associated with motor activities. This work introduces MOVING, a Multi-Modal dataset of EEG signals and Virtual Glove Hand Tracking. This dataset comprises neural EEG signals and kinematic data associated with three hand movements-open/close, finger tapping, and wrist rotation-along with a rest period. The dataset, obtained from 11 subjects using a 32-channel dry wireless EEG system, also includes synchronized kinematic data captured by a Virtual Glove (VG) system equipped with two orthogonal Leap Motion Controllers. The use of these two devices allows for fast assembly (∼1 min), although introducing more noise than the gold standard devices for data acquisition. The study investigates which frequency bands in EEG signals are the most informative for motor task classification and the impact of baseline reduction on gesture recognition. Deep learning techniques, particularly EEGnetV4, are applied to analyze and classify movements based on the EEG data. This dataset aims to facilitate advances in BCI research and in the development of assistive devices for people with impaired hand mobility. This study contributes to the repository of EEG datasets, which is continuously increasing with data from other subjects, which is hoped to serve as benchmarks for new BCI approaches and applications.

Removal of movement-induced EEG artifacts: current state of the art and guidelines

Electroencephalography (EEG) is a non-invasive technique used to record cortical neurons' electrical activity using electrodes placed on the scalp. It has become a promising avenue for research beyond state-of-the-art EEG research that is conducted under static conditions. EEG signals are always contaminated by artifacts and other physiological signals. Artifact contamination increases with the intensity of movement. In the last decade (since 2010), researchers have started to implement EEG measurements in dynamic setups to increase the overall ecological validity of the studies. Many different methods are used to remove non-brain activity from the EEG signal, and there are no clear guidelines on which method should be used in dynamic setups and for specific movement intensities. Currently, the most common methods for removing artifacts in movement studies are methods based on independent component analysis (ICA). However, the choice of method for artifact removal depends on the type and intensity of movement, which affects the characteristics of the artifacts and the EEG parameters of interest. When dealing with EEG under non-static conditions, special care must be taken already in the designing period of an experiment. Software and hardware solutions must be combined to achieve sufficient removal of unwanted signals from EEG measurements. We have provided recommendations for the use of each method depending on the intensity of the movement and highlighted the advantages and disadvantages of the methods. However, due to the current gap in the literature, further development and evaluation of methods for artifact removal in EEG data during locomotion is needed.

Advanced Bioelectrical Signal Processing Methods: Past, Present and Future Approach-Part II: Brain Signals

As it was mentioned in the previous part of this work (Part I)-the advanced signal processing methods are one of the quickest and the most dynamically developing scientific areas of biomedical engineering with their increasing usage in current clinical practice. In this paper, which is a Part II work-various innovative methods for the analysis of brain bioelectrical signals were presented and compared. It also describes both classical and advanced approaches for noise contamination removal such as among the others digital adaptive and non-adaptive filtering, signal decomposition methods based on blind source separation, and wavelet transform.

Detecting acute pain signals from human EEG

BACKGROUND

Advances in human neuroimaging has enabled us to study functional connections among various brain regions in pain states. Despite a wealth of studies at high anatomic resolution, the exact neural signals for the timing of pain remain little known. Identifying the onset of pain signals from distributed cortical circuits may reveal the temporal dynamics of pain responses and subsequently provide important feedback for closed-loop neuromodulation for pain.

NEW METHOD

Here we developed an unsupervised learning method for sequential detection of acute pain signals based on multichannel human EEG recordings. Following EEG source localization, we used a state-space model (SSM) to detect the onset of acute pain signals based on the localized regions of interest (ROIs).

RESULTS

We validated the SSM-based detection strategy using two human EEG datasets, including one public EEG recordings of 50 subjects. We found that the detection accuracy varied across tested subjects and detection methods. We also demonstrated the feasibility for cross-subject and cross-modality prediction of detecting the acute pain signals.

COMPARISON WITH EXISTING METHODS

In contrast to the batch supervised learning analysis based on a support vector machine (SVM) classifier, the unsupervised learning method requires fewer number of training trials in the online experiment, and shows comparable or improved performance than the supervised method.

CONCLUSIONS

Our unsupervised SSM-based method combined with EEG source localization showed robust performance in detecting the onset of acute pain signals.

Asynchronous Prediction of Human Gait Intention in a Pseudo Online Paradigm Using Wavelet Transform

Prediction of human voluntary gait intention is a very significant task to ensure direct cortical control of real-life assistive technologies for locomotion rehabilitation. Neurophysiological studies provide that human voluntary gait intention is represented by slow DC potentials and power shifts in specific frequency ranges of brain wave, which can be detected 1.5- 2 seconds before the actual onset. The goal of this study was to determine whether it is possible to reliably detect the intention of voluntary gait 'starting' and 'stopping' intention before it takes place. A computational algorithm was designed to implement asynchronous prediction of gait intention in an offline and pseudo-online environment using support vector machine. Six healthy subjects participated in the study and performed self- paced voluntary gait cycles. A combination of advanced wavelet transform algorithms resulted in 88.23± 1.59% accuracy, 85.42± 4.03% sensitivity and 90.24± 2.78% specificity for intention of start detection and 87.04± 1.72% accuracy, 82.69± 4.13% sensitivity and 89.59± 3.04% specificity for intention to stop walking in offline testing. Additionally, the wavelet transform methods accompanied with threshold regulation and majority voting algorithm resulted in a True Positive Rate of 85.5± 5.0% and 81.2± 3.3% for 'start' and 'stop' prediction with 6.8± 0.7 and 9.4± 1.0 False Positives per Minute respectively in pseudo online testing. The average detection latencies were -1002 ± 603 ms and -943 ± 603 ms, respectively, for 'start' and 'stop' prediction. The study provides promising outcomes in terms of TPR, FP/min, and detection latency, which suggests that human voluntary gait intention can be predicted before the onset of movement.

Prediction of gait intention from pre-movement EEG signals: a feasibility study

BACKGROUND

Prediction of Gait intention from pre-movement Electroencephalography (EEG) signals is a vital step in developing a real-time Brain-computer Interface (BCI) for a proper neuro-rehabilitation system. In that respect, this paper investigates the feasibility of a fully predictive methodology to detect the intention to start and stop a gait cycle by utilizing EEG signals obtained before the event occurrence.

METHODS

An eight-channel, custom-made, EEG system with electrodes placed around the sensorimotor cortex was used to acquire EEG data from six healthy subjects and two amputees. A discrete wavelet transform-based method was employed to capture event related information in alpha and beta bands in the time-frequency domain. The Hjorth parameters, namely activity, mobility, and complexity, were extracted as features while a two-sample unpaired Wilcoxon test was used to get rid of redundant features for better classification accuracy. The feature set thus obtained was then used to classify between 'walk vs. stop' and 'rest vs. start' classes using support vector machine (SVM) classifier with RBF kernel in a ten-fold cross-validation scheme.

RESULTS

Using a fully predictive intention detection system, 76.41±4.47% accuracy, 72.85±7.48% sensitivity, and 79.93±5.50% specificity were achieved for 'rest vs. start' classification. While for 'walk vs. stop' classification, the obtained mean accuracy, sensitivity, and specificity were 74.12±4.12%, 70.24±6.45%, and 77.78±7.01% respectively. Overall average True Positive Rate achieved by this methodology was 72.06±8.27% with 1.45 False Positives/min.

CONCLUSION

Extensive simulations and resulting classification results show that it is possible to achieve statistically similar intention detection accuracy using either only pre-movement EEG features or trans-movement EEG features. The classifier performance shows the potential of the proposed methodology to predict human movement intention exclusively from the pre-movement EEG signal to be applied in real-life prosthetic and neuro-rehabilitation systems.

Online Automatic Artifact Rejection using the Real-time EEG Source-mapping Toolbox (REST)

Non-brain contributions to electroencephalographic (EEG) signals, often referred to as artifacts, can hamper the analysis of scalp EEG recordings. This is especially true when artifacts have large amplitudes (e.g., movement artifacts), or occur continuously (like eye-movement artifacts). Offline automated pipelines can detect and reduce artifact in EEG data, but no good solution exists for online processing of EEG data in near real time. Here, we propose the combined use of online artifact subspace reconstruction (ASR) to remove large amplitude transients, and online recursive independent component analysis (ORICA) combined with an independent component (IC) classifier to compute, classify, and remove artifact ICs. We demonstrate the efficacy of the proposed pipeline using 2 EEG recordings containing series of (1) movement and muscle artifacts, and (2) cued blinks and saccades. This pipeline is freely available in the Real-time EEG Sourcemapping Toolbox (REST) for MATLAB (The Mathworks, Inc.).

Evaluation of Artifact Subspace Reconstruction for Automatic Artifact Components Removal in Multi-Channel EEG Recordings

OBJECTIVE

Artifact subspace reconstruction (ASR) is an automatic, online-capable, component-based method that can effectively remove transient or large-amplitude artifacts contaminating electroencephalographic (EEG) data. However, the effectiveness of ASR and the optimal choice of its parameter have not been systematically evaluated and reported, especially on actual EEG data.

METHODS

This paper systematically evaluates ASR on 20 EEG recordings taken during simulated driving experiments. Independent component analysis (ICA) and an independent component classifier are applied to separate artifacts from brain signals to quantitatively assess the effectiveness of the ASR.

RESULTS

ASR removes more eye and muscle components than brain components. Even though some eye and muscle components retain after ASR cleaning, the power of their temporal activities is reduced. Study results also showed that ASR cleaning improved the quality of a subsequent ICA decomposition.

CONCLUSIONS

Empirical results show that the optimal ASR parameter is between 20 and 30, balancing between removing non-brain signals and retaining brain activities.

SIGNIFICANCE

With an appropriate choice of parameter, ASR can be a powerful and automatic artifact removal approach for offline data analysis or online real-time EEG applications such as clinical monitoring and brain-computer interfaces.

ICLabel: An automated electroencephalographic independent component classifier, dataset, and website

The electroencephalogram (EEG) provides a non-invasive, minimally restrictive, and relatively low-cost measure of mesoscale brain dynamics with high temporal resolution. Although signals recorded in parallel by multiple, near-adjacent EEG scalp electrode channels are highly-correlated and combine signals from many different sources, biological and non-biological, independent component analysis (ICA) has been shown to isolate the various source generator processes underlying those recordings. Independent components (IC) found by ICA decomposition can be manually inspected, selected, and interpreted, but doing so requires both time and practice as ICs have no order or intrinsic interpretations and therefore require further study of their properties. Alternatively, sufficiently-accurate automated IC classifiers can be used to classify ICs into broad source categories, speeding the analysis of EEG studies with many subjects and enabling the use of ICA decomposition in near-real-time applications. While many such classifiers have been proposed recently, this work presents the ICLabel project comprised of (1) the ICLabel dataset containing spatiotemporal measures for over 200,000 ICs from more than 6000 EEG recordings and matching component labels for over 6000 of those ICs, all using common average reference, (2) the ICLabel website for collecting crowdsourced IC labels and educating EEG researchers and practitioners about IC interpretation, and (3) the automated ICLabel classifier, freely available for MATLAB. The ICLabel classifier improves upon existing methods in two ways: by improving the accuracy of the computed label estimates and by enhancing its computational efficiency. The classifier outperforms or performs comparably to the previous best publicly available automated IC component classification method for all measured IC categories while computing those labels ten times faster than that classifier as shown by a systematic comparison against other publicly available EEG IC classifiers.

Attenuated mismatch negativity in patients with first-episode antipsychotic-naive schizophrenia using a source-resolved method

BACKGROUND

Mismatch negativity (MMN) is a measure of pre-attentive auditory information processing related to change detection. Traditional scalp-level EEG methods consistently find attenuated MMN in patients with chronic but not first-episode schizophrenia. In the current paper, we use a source-resolved method to assess MMN and hypothesize that more subtle changes can be identified with this analysis method.

METHOD

Fifty-six first-episode antipsychotic-naïve schizophrenia (FEANS) patients (31 males, 25 females, mean age 24.6) and 64 matched controls (37 males, 27 females, mean age 24.8) were assessed for duration-, frequency- and combined-type MMN and P3a as well as 4 clinical, 3 cognitive and 3 psychopathological measures. To evaluate and correlate MMN at source-level, independent component analysis (ICA) was applied to the continuous EEG data to derive equivalent current dipoles which were clustered into 19 clusters based on cortical location.

RESULTS

No scalp channel group MMN or P3a amplitude differences were found. Of the localized clusters, several were in or near brain areas previously suggested to be involved in the MMN response, including frontal and anterior cingulate cortices and superior temporal and inferior frontal gyri. For duration deviants, MMN was attenuated at the right superior temporal gyrus in patients compared to healthy controls (p = 0.01), as was P3a at the superior frontal cortex (p = 0.01). No individual patient correlations with clinical, cognitive, or psychopathological measures survived correction for multiple comparisons.

CONCLUSION

Attenuated source-localized MMN and P3a peak contributions can be identified in FEANS patients using a method based on independent component analysis (ICA). This indicates that deficits in pre-attentive auditory information processing are present at this early stage of schizophrenia and are not the result of disease chronicity or medication. This is to our knowledge the first study on FEANS patients using this more detailed method.

Automatic Independent Component Scalp Map Analysis of Electroencephalogram During Motor Preparation

This work presents a method for automatic independent component (IC) scalp map analysis of electroencephalogram during motor preparation in visuomotor tasks. The strength of this approach is the analysis of the IC scalp maps based on the apriori given mask. This uses an image processing approach, comparable to visual classification used by experts, to automate the selection of relevant ICs in visuomotor tasks. Thirty iterations of the Infomax ICA algorithm were used to test the reliability of the ICs. ICs above 95% quality index were used for IC scalp topography image analysis. Here, we used a linkage-clustering algorithm for IC clustering and gap statistic to estimate the number of clusters. After classifying the components with our approach, the labels were compared to those from well-known MARA ("Multiple Artifact Rejection Algorithm") - an open-source EEGLAB plug-in. It was found that 334 of the 568 labels were in-agreement. MARA labeled 81 out of the 177 source-related components, and 238 out of the 319 non-source-related components, as artifacts. Here, the strength of our approach lies in using an image-processing algorithm to identify the task-specific ICs whereas MARA focuses on the automatic classification of the artifactual ICs by combining stereotyped artifact-specific spatial and temporal features that depend on the electrode montage. After "artefactual" ICs are removed, task-specific ICs still remains to be identified from the remaining "good" ICs where our scalp topography image analysis approach can be applied. Our IC scalp topography image analysis is focused on task-specific IC selection based on an apriori mask, which is not limited to specific EEG features and/or electrode configurations for high-density EEG.

Automated EEG artifact elimination by applying machine learning algorithms to ICA-based features

OBJECTIVE

Biological and non-biological artifacts cause severe problems when dealing with electroencephalogram (EEG) recordings. Independent component analysis (ICA) is a widely used method for eliminating various artifacts from recordings. However, evaluating and classifying the calculated independent components (IC) as artifact or EEG is not fully automated at present.

APPROACH

In this study, we propose a new approach for automated artifact elimination, which applies machine learning algorithms to ICA-based features.

MAIN RESULTS

We compared the performance of our classifiers with the visual classification results given by experts. The best result with an accuracy rate of 95% was achieved using features obtained by range filtering of the topoplots and IC power spectra combined with an artificial neural network.

SIGNIFICANCE

Compared with the existing automated solutions, our proposed method is not limited to specific types of artifacts, electrode configurations, or number of EEG channels. The main advantages of the proposed method is that it provides an automatic, reliable, real-time capable, and practical tool, which avoids the need for the time-consuming manual selection of ICs during artifact removal.

Real-Time Adaptive EEG Source Separation Using Online Recursive Independent Component Analysis

Independent component analysis (ICA) has been widely applied to electroencephalographic (EEG) biosignal processing and brain-computer interfaces. The practical use of ICA, however, is limited by its computational complexity, data requirements for convergence, and assumption of data stationarity, especially for high-density data. Here we study and validate an optimized online recursive ICA algorithm (ORICA) with online recursive least squares (RLS) whitening for blind source separation of high-density EEG data, which offers instantaneous incremental convergence upon presentation of new data. Empirical results of this study demonstrate the algorithm's: 1) suitability for accurate and efficient source identification in high-density (64-channel) realistically-simulated EEG data; 2) capability to detect and adapt to nonstationarity in 64-ch simulated EEG data; and 3) utility for rapidly extracting principal brain and artifact sources in real 61-channel EEG data recorded by a dry and wearable EEG system in a cognitive experiment. ORICA was implemented as functions in BCILAB and EEGLAB and was integrated in an open-source Real-time EEG Source-mapping Toolbox (REST), supporting applications in ICA-based online artifact rejection, feature extraction for real-time biosignal monitoring in clinical environments, and adaptable classifications in brain-computer interfaces.