An Unsupervised Multichannel Artifact Detection Method for Sleep EEG Based on Riemannian Geometry

Dusk2Dawn: an EEGLAB plugin for automatic cleaning of whole-night sleep electroencephalogram using Artifact Subspace Reconstruction

Whole-night sleep electroencephalogram (EEG) is plagued by several types of large-amplitude artifacts. Common approaches to remove them are fraught with issues: channel interpolation, rejection of noisy intervals, and independent component analysis are time-consuming, rely on subjective user decisions, and result in signal loss. Artifact Subspace Reconstruction (ASR) is an increasingly popular approach to rapidly and automatically clean wake EEG data. Indeed, ASR adaptively removes large-amplitude artifacts regardless of their scalp topography or consistency throughout the recording. This makes ASR, at least in theory, a highly-promising tool to clean whole-night EEG. However, ASR crucially relies on calibration against a subset of relatively clean "baseline" data. This is problematic when the baseline changes substantially over time, as in whole-night EEG data. Here we tackled this issue and, for the first time, validated ASR for cleaning sleep EEG. We demonstrate that ASR applied out-of-the-box, with the parameters recommended for wake EEG, results in the dramatic removal of slow waves. We also provide an appropriate procedure to use ASR for automatic and rapid cleaning of whole-night sleep EEG data or any long EEG recording. Our procedure is freely available in Dusk2Dawn, an open-source plugin for EEGLAB.

Mind wandering state detection during video-based learning via EEG

The aim of this study is to explore the potential of technology for detecting mind wandering, particularly during video-based distance learning, with the ultimate benefit of improving learning outcomes. To overcome the challenges of previous mind wandering research in ecological validity, sample balance, and dataset size, this study utilized practical electroencephalography (EEG) recording hardware and designed a paradigm consisting of viewing short-duration video lectures under a focused learning condition and a future planning condition. Participants estimated statistics of their attentional state at the end of each video, and we combined this rating scale feedback with self-caught key press responses during video watching to obtain binary labels for classifier training. EEG was recorded using an 8-channel system, and spatial covariance features processed by Riemannian geometry were employed. The results demonstrate that a radial basis function kernel support vector machine classifier, using Riemannian-processed covariance features from delta, theta, alpha, and beta bands, can detect mind wandering with a mean area under the receiver operating characteristic curve (AUC) of 0.876 for within-participant classification and AUC of 0.703 for cross-lecture classification. Furthermore, our results suggest that a short duration of training data is sufficient to train a classifier for online decoding, as cross-lecture classification remained at an average AUC of 0.689 when using 70% of the training set (about 9 min). The findings highlight the potential for practical EEG hardware in detecting mind wandering with high accuracy, which has potential application to improving learning outcomes during video-based distance learning.

'High-Density-SleepCleaner': An open-source, semi-automatic artifact removal routine tailored to high-density sleep EEG

BACKGROUND

With up to 256 channels, high-density electroencephalography (hd-EEG) has become essential to the sleep research field. The vast amount of data resulting from this magnitude of channels in overnight EEG recordings complicates the removal of artifacts.

NEW METHOD

We present a new, semi-automatic artifact removal routine specifically designed for sleep hd-EEG recordings. By employing a graphical user interface (GUI), the user assesses epochs in regard to four sleep quality markers (SQMs). Based on their topography and underlying EEG signal, the user eventually removes artifactual values. To identify artifacts, the user is required to have basic knowledge of the typical (patho-)physiological EEG they are interested in, as well as artifactual EEG. The final output consists of a binary matrix (channels x epochs). Channels affected by artifacts can be restored in afflicted epochs using epoch-wise interpolation, a function included in the online repository.

RESULTS

The routine was applied in 54 overnight sleep hd-EEG recordings. The proportion of bad epochs highly depends on the number of channels required to be artifact-free. Between 95% and 100% of bad epochs could be restored using epoch-wise interpolation. We furthermore present a detailed examination of two extreme cases (with few and many artifacts). For both nights, the topography and cyclic pattern of delta power look as expected after artifact removal.

COMPARISON WITH EXISTING METHODS

Numerous artifact removal methods exist, yet their scope of application usually targets short wake EEG recordings. The proposed routine provides a transparent, practical, and efficient approach to identify artifacts in overnight sleep hd-EEG recordings.

CONCLUSION

This method reliably identifies artifacts simultaneously in all channels and epochs.

Understanding the nonlinear behavior of EEG with advanced machine learning in artifact elimination

Steady-state Visually Evoked Potential (SSVEP) based Electroencephalogram (EEG) signal is utilized in brain-computer interface paradigms, diagnosis of brain diseases, and measurement of the cognitive status of the human brain. However, various artifacts such as the Electrocardiogram (ECG), Electrooculogram (EOG), and Electromyogram (EMG) are present in the raw EEG signal, which adversely affect the EEG-based appliances. In this research, Adaptive Neuro-fuzzy Interface Systems (ANFIS) and Hilbert-Huang Transform (HHT) are primarily employed to remove the artifacts from EEG signals. This work proposes Adaptive Noise Cancellation (ANC) and ANFIS based methods for canceling EEG artifacts. A mathematical model of EEG with the aforementioned artifacts is determined to accomplish the research goal, and then those artifacts are eliminated based on their mathematical characteristics. ANC, ANFIS, and HHT algorithms are simulated on the MATLAB platform, and their performances are also justified by various error estimation criteria using hardware implementation.

Boosting automated sleep staging performance in big datasets using population subgrouping

Current approaches to automated sleep staging from the electroencephalogram (EEG) rely on constructing a large labeled training and test corpora by aggregating data from different individuals. However, many of the subjects in the training set may exhibit changes in the EEG that are very different from the subjects in the test set. Training an algorithm on such data without accounting for this diversity can cause underperformance. Moreover, test data may have unexpected sensor misplacement or different instrument noise and spectral responses. This work proposes a novel method to learn relevant individuals based on their similarities effectively. The proposed method embeds all training patients into a shared and robust feature space. Individuals who share strong statistical relationships and are similar based on their EEG signals are clustered in this feature space before being passed to a deep learning framework for classification. Using 994 patient EEGs from the 2018 Physionet Challenge (≈6,561 h of recording), we demonstrate that the clustering approach significantly boosts performance compared to state-of-the-art deep learning approaches. The proposed method improves, on average, a precision score from 0.72 to 0.81, a sensitivity score from 0.74 to 0.82, and a Cohen's Kappa coefficient from 0.64 to 0.75 under 10-fold cross-validation.

Introduction: An overview of NIMH (Klecany, CZ) scientific activities

An overview of research activities of National Institute of Mental Health (NIMH) in Klecany, Czech republic. The institute was funded by EU operational project Research and Development for Innovation and started working in 2015. NIMH activities are organized in eight research programs including the neurobiology of the serious mental disorders, social psychiatry, brain imaging and use of information technologies in psychiatric research, epidemiology of addictions, sleep laboratory and chronobiology, electrophysiology, clinical research, and transfer of technologies. The equipment and expertise ranks NIMH Klecany among top neuroscience research institutions in central and eastern Europe.