https://www.mdu.se/

ElectroEncephaloGram (EEG) spectral power has been extensively used to classify Mental Imagery (MI) of movements involving different body parts. However, there is an increasing need to enable classification of MI of movements within the same limb. In this work, EEG spectral power was recorded in seven subjects while they performed MI of closing (grip) and opening (extension of fingers) the hand. The EEG data was analyzed and the feasibility of classifying MI of the two movements were investigated using two different classification algorithms, a linear regression and a Convolutional Neural Network (CNN). Results show that only the CNN is able to significantly classify MI of opening and closing of the hand with an average classification accuracy of 60.4%. This indicates the presence of higher-order non-linear discriminatory information and demonstrates the potential of using CNN in classifying MI of same-limb movements.

Motor Imagery (MI) classification from neural activity is thought to represent valuable information that can be provided as real-time feedback during rehabilitation after for example a stroke. Previous studies have suggested that MI induces partly subject-specific EEG activation patterns, suggesting that individualized classification models should be created. However, due to fatigue of the user, only a limited number of samples can be recorded and, for EEG recordings, each sample is often composed of a large number of features. This combination leads to an undesirable input data set for classification. In order to overcome this constraint, we propose a new methodology to create and select features from the EEG signal in two steps. First, the input data is divided into different windows to reduce the cardinality of the input. Secondly, a Hierarchical Genetic Algorithm is used to select relevant features using a novel fitness function which combines the data reduction with a correlation feature selection measure. The methodology has been tested on EEG oscillatory activity recorded from 6 healthy volunteers while they performed an MI task. Results have successfully proven that a classification above 75% can be obtained in a restrictive amount of time (0.02 s), reducing the number of features by almost 90%.

Neurofeedback in real-time has proven effective when subjects learn to control a BCI. To facilitate learning, a closed-loop feedback system should provide neurofeedback with maximal accuracy and minimal delay. In this article, we propose a modular system for real-time neurofeedback experiments and evaluate its performance as a function of increased stress level applied to the system. The system shows stable behavior and decent performance when streaming with many EEG channels (36-72) and 500-5000 Hz, which is common in BCI setups. With very low data loads (1 channel, 500-1000 Hz) the performance dropped significantly and the system became highly unpredictable. We show that the system delays did not correlate linearly with the stress-level applied to the system, emphasizing the importance of system delay tests before conducting real-time BCI-experiments. 

OBJECTIVE: Multivariate decoding enables access to information encoded in multiple brain activity features with high temporal resolution. However, whether the strength, of which this information is represented in the brain, can be extracted across time within single trials remains largely unexplored.

APPROACH: In this study, we addressed this question by applying a Support Vector Machine (SVM) to extract Motor Imagery (MI) representations, from Electroencephalogram (EEG) data, and by performing time-resolved single-trial analyses of the multivariate decoding. EEG was recorded from a group of healthy participants during MI of opening and closing of the same hand.

MAIN RESULTS: Cross-temporal decoding revealed both dynamic and stationary MI-relevant features during the task. Specifically, features representing MI evolved dynamically early in the trial and later stabilized into a stationary network of MI features. Using a Hierarchical Genetic Algorithm (HGA) for selection of MI-relevant features, we identified primarily contralateral alpha and beta frequency features over the sensorimotor and parieto-occipital cortices as stationary which extended into a bilateral pattern in the later part of the trial. During the stationary encoding of MI, by extracting the SVM prediction scores, we analyzed MI-relevant EEG activity patterns with respect to the temporal dynamics within single trials. We show that the SVM prediction score correlates to the amplitude of univariate MI-relevant features (as documented from an extensive repertoire of previous MI studies) within single trials, strongly suggesting that these are functional variations of MI strength hidden in trial averages.

SIGNIFICANCE: Our work demonstrates a powerful approach for estimating MI strength continually within single trials, having far-reaching impact for single-trial analyses. In terms of MI neurofeedback for motor rehabilitation, these results set the ground for more refined neurofeedback reflecting the strength of MI that can be provided to patients continually in time.

Objective: Motor Imagery-based Brain-Computer Interfaces (MI-BCIs) is a promising technology for neurorehabilitation after stroke. However, many face challenges in using a BCI because they fail to produce discriminable patterns in their brain activity. Personalizing the BCI task difficulty could help the learning process of these users but there is currently very limited knowledge on which methods can be used online. Our aim was to explore a distance-to-bound approach for adapting MI BCI task difficulty in real time.

Approach: Two chronic stroke patients performed 12 BCI training sessions over 4 weeks during which they performed MI of open- and close hand movements and received continual visual feedback based on multivariate decoding of ongoing electroencephalogram (EEG) activity. The difficulty was increased and adapted in real time based on distance-to-bound decoding metrics and using a multiple-session design we investigated the stability of this approach and how it related to MI-related EEG activity of each patient.

Main results: We show that patients had to produce stronger alpha and beta event-related desynchronization (ERD) activity across the sensorimotor cortical areas of the brain to receive positive feedback. In addition, we show that the online adaptation converged within sessions as well as accommodating for drift in the data both within and between sessions. We suggest that the distance-to-bound approach can effectively be used to control BCI task difficulty and potentially guide patients to produce functionally relevant activity patterns. However, from our results, stronger sensorimotor ERD activity did not consistently correlate to improved motor function. Clinical assessments showed that both patients improved in motor function (+4 and +8.7 change in Fugl-Meyer assessment for upper extremity), however, the correlation to sensorimotor ERD activity was positive for one patient and negative for the other (Pearson’s rho = 0.95, -0.80, p = 0.05, 0.18). . Further, MI pattern strength correlated with clinical motor outcomes (Pearson’s rho = 0.993, -0.849, p = 0.007, 0.151), however positively for one patient and negatively for the other.These results indicate that the translation of distance-to-bound outputs to feedback needs to be individually tailored considering the stroke lesion and EEG activity profiles for each patient.

Significance: This study provides valuable insights and considerations for BCI difficulty adaptation in the aim of developing more effective training protocols in BCI-based stroke rehabilitation.

Abstract— Clinical Electroencephalogram (EEG) Brain- Computer-Interface (BCI) rehabilitation largely depend on reliable information extraction from steadily evolving brain features. Non-stationary EEG feature behavior is considered a major challenge and a lot of effort has been devoted to developing adaptive methods to accommodate for this nonstationarity. However, learning- and plasticity-related mechanisms throughout a BCI intervention are additional sources of non-stationarity, that even though expected, we know very little about. In this work, we explore the evolution of Motor Imagery (MI) information extraction across multiple sessions, in two stroke patients, using a fixed and an adaptive Support Vector Machine (SVM) model. We show different behavior of the fixed SVM model for the two patients, indicating that for one patient, relevant MI-related EEG features shifted throughout the intervention. This observation calls for further investigations to better understand the evolution and shift of features across sessions, as well as the impact of using adaptive methods from a clinical outcome perspective.