Time-Variant Linear Discriminant Analysis Improves Hand Gesture and Finger Movement Decoding for Invasive Brain-Computer Interfaces

Individual-finger motor imagery classification: a data-driven approach with Shapley-informed augmentation

Objective. Classifying motor imagery (MI) tasks that involve fine motor control of the individual five fingers presents unique challenges when utilizing electroencephalography (EEG) data. In this paper, we systematically assess the classification of MI functions for the individual five fingers using single-trial time-domain EEG signals. This assessment encompasses both within-subject and cross-subject scenarios, supported by data-driven analysis that provides statistical validation of the neural correlate that could potentially discriminate between the five fingers.Approach. We present Shapley-informed augmentation, an informed approach to enhance within-subject classification accuracy. This method is rooted in insights gained from our data-driven analysis, which revealed inconsistent temporal features encoding the five fingers MI across sessions of the same subject. To evaluate its impact, we compare within-subject classification performance both before and after implementing this augmentation technique.Main results. Both the data-driven approach and the model explainability analysis revealed that the parietal cortex contains neural information that helps discriminate the individual five fingers' MI apart. Shapley-informed augmentation successfully improved classification accuracy in sessions severely affected by inconsistent temporal features. The accuracy for sessions impacted by inconsistency in their temporal features increased by an average of26.3%±6.70, thereby enabling a broader range of subjects to benefit from brain-computer interaction (BCI) applications involving five-fingers MI classification. Conversely, non-impacted sessions experienced only a negligible average accuracy decrease of2.01±5.44%. The average classification accuracy achieved is around 60.0% (within-session), 50.0% (within-subject) and 40.0% (leave-one-subject-out).Significance. This research offers data-driven evidence of neural correlates that could discriminate between the individual five fingers MI and introduces a novel Shapley-informed augmentation method to address temporal variability of features, ultimately contributing to the development of personalized systems.

Characterization of High-Gamma Activity in Electrocorticographic Signals

Introduction

Electrocorticographic (ECoG) high-gamma activity (HGA) is a widely recognized and robust neural correlate of cognition and behavior. However, fundamental signal properties of HGA, such as the high-gamma frequency band or temporal dynamics of HGA, have never been systematically characterized. As a result, HGA estimators are often poorly adjusted, such that they miss valuable physiological information.

Methods

To address these issues, we conducted a thorough qualitative and quantitative characterization of HGA in ECoG signals. Our study is based on ECoG signals recorded from 18 epilepsy patients while performing motor control, listening, and visual perception tasks. In this study, we first categorize HGA into HGA types based on the cognitive/behavioral task. For each HGA type, we then systematically quantify three fundamental signal properties of HGA: the high-gamma frequency band, the HGA bandwidth, and the temporal dynamics of HGA.

Results

The high-gamma frequency band strongly varies across subjects and across cognitive/behavioral tasks. In addition, HGA time courses have lowpass character, with transients limited to 10 Hz. The task-related rise time and duration of these HGA time courses depend on the individual subject and cognitive/behavioral task. Task-related HGA amplitudes are comparable across the investigated tasks.

Discussion

This study is of high practical relevance because it provides a systematic basis for optimizing experiment design, ECoG acquisition and processing, and HGA estimation. Our results reveal previously unknown characteristics of HGA, the physiological principles of which need to be investigated in further studies.

Decoding and geometry of ten finger movements in human posterior parietal cortex and motor cortex

Objective. Enable neural control of individual prosthetic fingers for participants with upper-limb paralysis.Approach. Two tetraplegic participants were each implanted with a 96-channel array in the left posterior parietal cortex (PPC). One of the participants was additionally implanted with a 96-channel array near the hand knob of the left motor cortex (MC). Across tens of sessions, we recorded neural activity while the participants attempted to move individual fingers of the right hand. Offline, we classified attempted finger movements from neural firing rates using linear discriminant analysis with cross-validation. The participants then used the neural classifier online to control individual fingers of a brain-machine interface (BMI). Finally, we characterized the neural representational geometry during individual finger movements of both hands.Main Results. The two participants achieved 86% and 92% online accuracy during BMI control of the contralateral fingers (chance = 17%). Offline, a linear decoder achieved ten-finger decoding accuracies of 70% and 66% using respective PPC recordings and 75% using MC recordings (chance = 10%). In MC and in one PPC array, a factorized code linked corresponding finger movements of the contralateral and ipsilateral hands.Significance. This is the first study to decode both contralateral and ipsilateral finger movements from PPC. Online BMI control of contralateral fingers exceeded that of previous finger BMIs. PPC and MC signals can be used to control individual prosthetic fingers, which may contribute to a hand restoration strategy for people with tetraplegia.

Hyper-parameter tuning and feature extraction for asynchronous action detection from sub-thalamic nucleus local field potentials

Introduction

Decoding brain states from subcortical local field potentials (LFPs) indicative of activities such as voluntary movement, tremor, or sleep stages, holds significant potential in treating neurodegenerative disorders and offers new paradigms in brain-computer interface (BCI). Identified states can serve as control signals in coupled human-machine systems, e.g., to regulate deep brain stimulation (DBS) therapy or control prosthetic limbs. However, the behavior, performance, and efficiency of LFP decoders depend on an array of design and calibration settings encapsulated into a single set of hyper-parameters. Although methods exist to tune hyper-parameters automatically, decoders are typically found through exhaustive trial-and-error, manual search, and intuitive experience.

Methods

This study introduces a Bayesian optimization (BO) approach to hyper-parameter tuning, applicable through feature extraction, channel selection, classification, and stage transition stages of the entire decoding pipeline. The optimization method is compared with five real-time feature extraction methods paired with four classifiers to decode voluntary movement asynchronously based on LFPs recorded with DBS electrodes implanted in the subthalamic nucleus of Parkinson's disease patients.

Results

Detection performance, measured as the geometric mean between classifier specificity and sensitivity, is automatically optimized. BO demonstrates improved decoding performance from initial parameter setting across all methods. The best decoders achieve a maximum performance of 0.74 ± 0.06 (mean ± SD across all participants) sensitivity-specificity geometric mean. In addition, parameter relevance is determined using the BO surrogate models.

Discussion

Hyper-parameters tend to be sub-optimally fixed across different users rather than individually adjusted or even specifically set for a decoding task. The relevance of each parameter to the optimization problem and comparisons between algorithms can also be difficult to track with the evolution of the decoding problem. We believe that the proposed decoding pipeline and BO approach is a promising solution to such challenges surrounding hyper-parameter tuning and that the study's findings can inform future design iterations of neural decoders for adaptive DBS and BCI.

Nine decades of electrocorticography: A comparison between epidural and subdural recordings

In recent years, electrocorticography (ECoG) has arisen as a neural signal recording tool in the development of clinically viable neural interfaces. ECoG electrodes are generally placed below the dura mater (subdural) but can also be placed on top of the dura (epidural). In deciding which of these modalities best suits long-term implants, complications and signal quality are important considerations. Conceptually, epidural placement may present a lower risk of complications as the dura is left intact but also a lower signal quality due to the dura acting as a signal attenuator. The extent to which complications and signal quality are affected by the dura, however, has been a matter of debate. To improve our understanding of the effects of the dura on complications and signal quality, we conducted a literature review. We inventorized the effect of the dura on signal quality, decodability and longevity of acute and chronic ECoG recordings in humans and non-human primates. Also, we compared the incidence and nature of serious complications in studies that employed epidural and subdural ECoG. Overall, we found that, even though epidural recordings exhibit attenuated signal amplitude over subdural recordings, particularly for high-density grids, the decodability of epidural recorded signals does not seem to be markedly affected. Additionally, we found that the nature of serious complications was comparable between epidural and subdural recordings. These results indicate that both epidural and subdural ECoG may be suited for long-term neural signal recordings, at least for current generations of clinical and high-density ECoG grids.

Introducing block-Toeplitz covariance matrices to remaster linear discriminant analysis for event-related potential brain-computer interfaces

Objective.Covariance matrices of noisy multichannel electroencephalogram (EEG) time series data provide essential information for the decoding of brain signals using machine learning methods. However, small datasets and high dimensionality make it hard to estimate these matrices. In brain-computer interfaces (BCI) based on event-related potentials (ERP) and a linear discriminant analysis (LDA) classifier, the state of the art covariance estimation uses shrinkage regularization. As this is a general covariance regularization approach, we aim at improving LDA further by better exploiting the domain-specific characteristics of the EEG to regularize the covariance estimates.Approach.We propose to enforce a block-Toeplitz structure for the covariance matrix of the LDA, which implements an assumption of signal stationarity in short time windows for each channel.Main results.An offline re-analysis of data collected from 213 subjects under 13 different event-related potential BCI protocols showed a significantly increased binary classification performance of this 'ToeplitzLDA' compared to shrinkage regularized LDA (up to 6 AUC points,p < 0.001) and Riemannian classification approaches (up to 2 AUC points,p < 0.001). In an unsupervised visual speller application, this improvement would translate to a relative reduction of spelling errors by 81% on average for 25 subjects. Additionally, aside from lower memory and reduced time complexity for LDA training, ToeplitzLDA proves to be robust against drastic increases of the number of temporal features.Significance.The proposed covariance estimation allows BCI researchers to improve classification rates and reduce calibration times of BCI protocols using event-related potentials and thus support the usability of corresponding applications. Its lower computational and memory needs could make it a valuable algorithm especially for mobile BCIs.

Individual finger movement decoding using a novel ultra-high-density electroencephalography-based brain-computer interface system

Brain-Computer Interface (BCI) technology enables users to operate external devices without physical movement. Electroencephalography (EEG) based BCI systems are being actively studied due to their high temporal resolution, convenient usage, and portability. However, fewer studies have been conducted to investigate the impact of high spatial resolution of EEG on decoding precise body motions, such as finger movements, which are essential in activities of daily living. Low spatial sensor resolution, as found in common EEG systems, can be improved by omitting the conventional standard of EEG electrode distribution (the international 10-20 system) and ordinary mounting structures (e.g., flexible caps). In this study, we used newly proposed flexible electrode grids attached directly to the scalp, which provided ultra-high-density EEG (uHD EEG). We explored the performance of the novel system by decoding individual finger movements using a total of 256 channels distributed over the contralateral sensorimotor cortex. Dense distribution and small-sized electrodes result in an inter-electrode distance of 8.6 mm (uHD EEG), while that of conventional EEG is 60 to 65 mm on average. Five healthy subjects participated in the experiment, performed single finger extensions according to a visual cue, and received avatar feedback. This study exploits mu (8-12 Hz) and beta (13-25 Hz) band power features for classification and topography plots. 3D ERD/S activation plots for each frequency band were generated using the MNI-152 template head. A linear support vector machine (SVM) was used for pairwise finger classification. The topography plots showed regular and focal post-cue activation, especially in subjects with optimal signal quality. The average classification accuracy over subjects was 64.8 (6.3)%, with the middle versus ring finger resulting in the highest average accuracy of 70.6 (9.4)%. Further studies are required using the uHD EEG system with real-time feedback and motor imagery tasks to enhance classification performance and establish the basis for BCI finger movement control of external devices.

A Single-Channel Wireless EEG Headset Enabled Neural Activities Analysis for Mental Healthcare Applications

Electroencephalography (EEG) is a technique of Electrophysiology used in a wide variety of scientific studies and applications. Inadequately, many commercial devices that are available and used worldwide for EEG monitoring are expensive that costs up to thousands of dollars. Over the past few years, because of advancements in technology, different cost-effective EEG recording devices have been made. One such device is a non-invasive single electrode commercial EEG headset called MindWave 002 (MW2), created by NeuroSky Inc that cost less than 100 USD. This work contributes in four distinct ways, first, how mental states such as a focused and relaxed can be identified based on EEG signals recorded by inexpensive MW2 is demonstrated for accurate information extraction. Second, MW2 is considered because apart from cost, the user's comfort level is enhanced due to non-invasive operation, low power consumption, portable small size, and a minimal number of detecting locations of MW2. Third, 2 situations were created to stimulate focus and relaxation states. Prior to analysis, the acquired brain signals were pre-processed to discard artefacts and noise, and band-pass filtering was performed for delta, theta, alpha, beta, and gamma wave extraction. Fourth, analysis of the shapes and nature of extracted waves was performed with power spectral density (PSD), mean amplitude values, and other parameters in LabVIEW. Finally, with comprehensive experiments, the mean values of the focused and relaxed signal EEG signals were found to be 30.23 µV and 15.330 µV respectively. Similarly, average PSD values showed an increase in theta wave value and a decrease in beta wave value related to the focus and relaxed state, respectively. We also analyzed the involuntary and intentional number of blinks recorded by the MW2 device. Our study can be used to check mental health wellness and could provide psychological treatment effects by training the mind to quickly enter a relaxed state and improve the person's ability to focus. In addition, this study can open new avenues for neurofeedback and brain control applications.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11277-022-09731-w.

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.

Decoding of Hand Gestures from Electrocorticography with LSTM Based Deep Neural Network

Hand gesture decoding is a key component of controlling prosthesis in the area of Brain Computer Interface (BCI). This study is concerned with classification of hand gestures, based on Electrocorticography (ECoG) recordings. Recent studies have utilized the temporal information in ECoG signals for robust hand gesture decoding. In our preliminary analysis on ECoG recordings of hand gestures, we observed different power variations in six frequency bands ranging from 4 to 200 Hz. Therefore, the current trend of including temporal information in the classifier was extended to provide equal importance to power variations in each of these frequency bands. Statistical and Principal Component Analysis (PCA) based feature reduction was implemented for each frequency band separately, and classification was performed with a Long Short-Term Memory (LSTM) based neural network to utilize both temporal and spatial information of each frequency band. The proposed architecture along with each feature reduction method was tested on ECoG recordings of five finger flexions performed by seven subjects from the publicly available 'fingerflex' dataset. An average classification accuracy of 82.4% was achieved with the statistical based channel selection method which is an improvement compared to state-of-the-art methods.

EEG feature fusion for motor imagery: A new robust framework towards stroke patients rehabilitation

Stroke is the second foremost cause of death worldwide and is one of the most common causes of disability. Several approaches have been proposed to manage stroke patient rehabilitation such as robotic devices and virtual reality systems, and researchers have found that the brain-computer interfaces (BCI) approaches can provide better results. Therefore, the most challenging tasks with BCI applications involve identifying the best technique(s) that can reveal the neuron stimulus information from the patients' brains and extracting the most effective features from these signals as well. Accordingly, the main novelty of this paper is twofold: propose a new feature fusion method for motor imagery (MI)-based BCI and develop an automatic MI framework to detect the changes pre- and post-rehabilitation. This study investigated the electroencephalography (EEG) dataset from post-stroke patients with upper extremity hemiparesis. All patients performed 25 MI-based BCI sessions with follow up assessment visits to examine the functional changes before and after EEG neurorehabilitation. In the first stage, conventional filters and automatic independent component analysis with wavelet transform (AICA-WT) denoising technique were used. Next, attributes from time, entropy and frequency domains were computed, and the effective features were combined into time-entropy-frequency (TEF) attributes. Consequently, the AICA-WT and the TEF fusion set were utilised to develop an AICA-WT-TEF framework. Then, support vector machine (SVM), k-nearest neighbours (kNN) and random forest (RF) classification technique were tested for MI-based BCI rehabilitation. The proposed AICA-WT-TEF framework with RF classifier achieves the best results compared with other classifiers. Finally, the proposed framework and feature fusion set achieve a significant performance in terms of accuracy measures compared to the state-of-the-art. Therefore, the proposed methods could be crucial for improving the process of automatic MI rehabilitation and are recommended for implementation in real-time applications.

Evaluating a Novel P300-Based Real-Time Image Ranking BCI

Brain–computer interfaces (BCIs) establish communication between a human brain and a computer or external devices by translating the electroencephalography (EEG) signal into computer commands. After stimulating a sensory organ, a positive deflection of the EEG signal between 250 and 700 ms can be measured. This signal component of the event-related potential (ERP) is called “P300.” Numerous studies have provided evidence that the P300 amplitude and latency are linked to sensory perception, engagement, and cognition. Combining the advances in technology, classification methods, and signal processing, we developed a novel image ranking system called the Unicorn Blondy Check. In this study, the application was tested on 21 subjects using three different visual oddball paradigms. Two consisted of female faces and gray-scale images, while the third test paradigm consisted of familiar and unfamiliar faces. The images were displayed for a duration of 150 ms in a randomized order. The system was trained using 50 trials and tested with 30 trials. The EEG data were acquired using the Unicorn Hybrid Black eight-channel BCI system. These synchronized recordings were analyzed, and the achieved classification accuracies were calculated. The EEG signal was averaged over all participants and for every paradigm separately. Analysis of the EEG data revealed a significant shift in the P300 latency dependent on the paradigm and decreased amplitude for a lower target to non-target ratio. The image ranking application achieved a mean accuracy of 100 and 95.5% for ranking female faces above gray-scale images with ratios of 1:11 and 5:11, respectively. In the case of four familiar faces to 24 unfamiliar faces, 86.4% was reached. The obtained results illustrate this novel system’s functionality due to accuracies above chance levels for all subjects.