The Organization for Human Brain Mapping (OHBM) has been active in advocating for the instantiation of best practices in neuroimaging data acquisition, analysis, reporting and sharing of both data and analysis code to deal with issues in science related to reproducibility and replicability. Here we summarize recommendations for such practices in magnetoencephalographic (MEG) and electroencephalographic (EEG) research, recently developed by the OHBM neuroimaging community known by the abbreviated name of COBIDAS MEEG. We discuss the rationale for the guidelines and their general content, which encompass many topics under active discussion in the field. We highlight future opportunities and challenges to maximizing the sharing and exploitation of MEG and EEG data, and we also discuss how this 'living' set of guidelines will evolve to continually address new developments in neurophysiological assessment methods and multimodal integration of neurophysiological data with other data types.

/pdf/issues-and-recommendations-from-the-ohbm-cobidas-meeg-4tq7ydd1aa.pdf

Issues and recommendations from the OHBM COBIDAS MEEG committee for reproducible EEG and MEG research.

https://www.zora.uzh.ch/id/eprint/189024/1/1-s2.0-S1053811920304201-main.pdf

Neural dynamics of sentiment processing during naturalistic sentence reading.

Objective.Semantic decoding refers to the identification of semantic concepts from recordings of an individual's brain activity. It has been previously reported in functional magnetic resonance imaging and electroencephalography. We investigate whether semantic decoding is possible with functional near-infrared spectroscopy (fNIRS). Specifically, we attempt to differentiate between the semantic categories of animals and tools. We also identify suitable mental tasks for potential brain-computer interface (BCI) applications.Approach.We explore the feasibility of a silent naming task, for the first time in fNIRS, and propose three novel intuitive mental tasks based on imagining concepts using three sensory modalities: visual, auditory, and tactile. Participants are asked to visualize an object in their minds, imagine the sounds made by the object, and imagine the feeling of touching the object. A general linear model is used to extract hemodynamic responses that are then classified via logistic regression in a univariate and multivariate manner.Main results.We successfully classify all tasks with mean accuracies of 76.2% for the silent naming task, 80.9% for the visual imagery task, 72.8% for the auditory imagery task, and 70.4% for the tactile imagery task. Furthermore, we show that consistent neural representations of semantic categories exist by applying classifiers across tasks.Significance.These findings show that semantic decoding is possible in fNIRS. The study is the first step toward the use of semantic decoding for intuitive BCI applications for communication.

https://iopscience.iop.org/article/10.1088/1741-2552/abf2e5/pdf

Decoding of semantic categories of imagined concepts of animals and tools in fNIRS.

This work explores techniques to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution with electroencephalography (EEG) during text reading. We first show that information about word length, frequency and word class is encoded by the brain at different post-stimulus latencies. We then demonstrate that pre-training on averaged EEG data and data augmentation techniques boost PoS decoding accuracy for single EEG trials. Finally, applying optimised temporally-resolved decoding techniques we show that Transformers substantially outperform linear-SVMs on PoS tagging of unigram and bigram data.

Decoding Part-of-Speech from Human EEG Signals

Rapid serial visual presentation (RSVP) is an effective brain-computer interface (BCI) technique for recognizing target objects. Decoding the subject’s intention from the single-trial electroencephalogram (EEG) signal through a decoding algorithm is the key to RSVP-based BCI. The unavoidable noise and variability between trials in EEG signals lead to low accuracy of EEG-based RSVP detection and low universality of the model. It is necessary to develop an EEG decoding algorithm with robust generalization ability and high recognition accuracy. In this study, we proposed a novel end-to-end model architecture that combines multi-scale spatiotemporal convolutional neural network (CNN) and Transformers. Specifically, the multi-scale CNN is used to capture spatiotemporal features at different scales, while the Transformers are used to extract the most discriminative global information. Experimental results on the RSVP-based benchmark datasets show that the proposed method in this study can achieve higher recognition accuracy compared to the other three advanced methods in both cross-subject and within-subject experiments. The results of fine-tuning experiments using pre-trained models on a new subject show that better results can be obtained in single-subject experiments using only a small amount of data. The experimental results validate the effectiveness of our method and provide a new idea for constructing a feature extraction method with better generalization capability for RSVP-based BCI. 

Combining multi-scale convolutional neural network and Transformers for EEG-Based RSVP detection

There is significant current interest in decoding mental states from electroencephalography (EEG) recordings. EEG signals are subject-specific, are sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that support vector machine (SVM) classifiers trained on a relatively small set of denoised (averaged) pseudotrials perform on par with classifiers trained on a large set of noisy single-trial samples. We propose a novel method for computing sensitivity maps of EEG-based SVM classifiers for visualization of EEG signatures exploited by the SVM classifiers. Moreover, we apply an NPAIRS resampling framework for estimation of map uncertainty, and thus show that effect sizes of sensitivity maps for classifiers trained on small samples of denoised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudotrial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization, and unbiased performance evaluation in machine learning approaches for brain decoding.

/pdf/single-trial-decoding-of-scalp-eeg-under-natural-conditions-6rnr6mqvuv.pdf

Single-Trial Decoding of Scalp EEG under Natural Conditions

There is significant current interest in decoding mental states from electro-encephalography (EEG) recordings. EEG signals are subject-specific, sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that Support Vector Machine (SVM) classifiers trained on a relatively small set of de-noised (averaged) pseudo-trials perform on par with classifiers trained on a large set of noisy single-trial samples. For visualization of EEG signatures exploited by SVM classifiers, we propose a novel method for computing sensitivity maps of EEG-based SVM classifiers. Moreover, we apply the NPAIRS resampling framework for estimation of map uncertainty and show that effect sizes of sensitivity maps for classifiers trained on small samples of de-noised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudo-trial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization and unbiased performance evaluation in machine learning approaches for brain decoding.

/pdf/single-trial-decoding-of-scalp-eeg-under-natural-conditions-3h17vcp8dv.pdf

Single-Trial Decoding of Scalp EEG Under Natural Conditions

There is significant current interest in decoding mental states from electro-encephalography (EEG) recordings. We demonstrate single trial decoding of naturalistic stimuli based on scalp EEG acquired with user-friendly, portable, 32 dry electrode equipment. We show that Support Vector Machine (SVM) classifiers trained on a relatively small set of de-noised (averaged) trials perform at par with classifiers trained on a large set of noisy samples. We propose a novel method for computing sensitivity maps on EEG-based SVM classifiers for visualization of the EEG signatures exploited by SVM classifiers. We apply the NPAIRS framework for estimation of map uncertainty. We show that effect size plots are similar for classifiers trained on small samples of de-noised data and large samples of noisy data. We conclude that the average category classifier can successfully predict on single-trial subjects, allowing for fast classifier training, parameter optimization and unbiased performance evaluation.

/pdf/single-trial-decoding-of-scalp-eeg-under-naturalistic-42zgn8rw2i.pdf

Dea Steenstrup

Papers

Single-Trial Decoding of Scalp EEG under Natural Conditions

Single-Trial Decoding of Scalp EEG Under Natural Conditions

Single Trial Decoding of Scalp EEG Under Naturalistic Stimuli