An Adaptive Brain-Computer Interface to Enhance Motor Recovery After Stroke.

Brain computer interfaces (BCIs) have been demonstrated to have the potential to enhance motor recovery after stroke. However, some stroke patients with severe paralysis have difficulty achieving the BCI performance required for participating in BCI-based rehabilitative interventions, limiting their clinical benefits. To address this issue, we presented a BCI intervention approach that can adapt to patients' BCI performance and reported that adaptive BCI-based functional electrical stimulation (FES) treatment induced clinically significant, long-term improvements in upper extremity motor function after stroke more effectively than FES treatment without BCI intervention. These improvements were accompanied by a more optimized brain functional reorganization. Further comparative analysis revealed that stroke patients with low BCI performance (LBP) had no significant difference from patients with high BCI performance in rehabilitation efficacy improvement. Our findings suggested that the current intervention may be an effective way for LBP patients to engage in BCI-based rehabilitation treatment and may promote lasting motor recovery, thus contributing to expanding the applicability of BCI-based rehabilitation treatments to pave the way for more effective rehabilitation treatments.

EEG-Based Driving Fatigue Detection Using a Two-Level Learning Hierarchy Radial Basis Function.

Electroencephalography (EEG)-based driving fatigue detection has gained increasing attention recently due to the non-invasive, low-cost, and potable nature of the EEG technology, but it is still challenging to extract informative features from noisy EEG signals for driving fatigue detection. Radial basis function (RBF) neural network has drawn lots of attention as a promising classifier due to its linear-in-the-parameters network structure, strong non-linear approximation ability, and desired generalization property. The RBF network performance heavily relies on network parameters such as the number of the hidden nodes, number of the center vectors, width, and output weights. However, global optimization methods that directly optimize all the network parameters often result in high evaluation cost and slow convergence. To enhance the accuracy and efficiency of EEG-based driving fatigue detection model, this study aims to develop a two-level learning hierarchy RBF network (RBF-TLLH) which allows for global optimization of the key network parameters. Experimental EEG data were collected, at both fatigue and alert states, from six healthy participants in a simulated driving environment. Principal component analysis was first utilized to extract features from EEG signals, and the proposed RBF-TLLH was then employed for driving status (fatigue vs. alert) classification. The results demonstrated that the proposed RBF-TLLH approach achieved a better classification performance (mean accuracy: 92.71%; area under the receiver operating curve: 0.9199) compared to other widely used artificial neural networks. Moreover, only three core parameters need to be determined using the training datasets in the proposed RBF-TLLH classifier, which increases its reliability and applicability. The findings demonstrate that the proposed RBF-TLLH approach can be used as a promising framework for reliable EEG-based driving fatigue detection.

Multimodal Neuroimaging Using Concurrent EEG/fNIRS for Poststroke Recovery Assessment: An Exploratory Study.

BACKGROUND: Persistent motor deficits are very common in poststroke survivors and often lead to disability. Current clinical measures for profiling motor impairment and assessing poststroke recovery are largely subjective and lack precision. OBJECTIVE: A multimodal neuroimaging approach was developed based on concurrent functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) to identify biomarkers associated with motor function recovery and document the poststroke cortical reorganization. METHODS: EEG and fNIRS data were simultaneously recorded from 9 healthy controls and 18 stroke patients during a hand-clenching task. A novel fNIRS-informed EEG source imaging approach was developed to estimate cortical activity and functional connectivity. Subsequently, graph theory analysis was performed to identify network features for monitoring and predicting motor function recovery during a 4-week intervention. RESULTS: The task-evoked strength at ipsilesional primary somatosensory cortex was significantly lower in stroke patients compared with healthy controls (P < .001). In addition, across the 4-week rehabilitation intervention, the strength at ipsilesional premotor cortex (PMC) (R = 0.895, P = .006) and the connectivity between bilateral primary motor cortices (M1) (R = 0.9, P = .007) increased in parallel with the improvement of motor function. Furthermore, a higher baseline strength at ipsilesional PMC was associated with a better motor function recovery (R = 0.768, P = .007), while a higher baseline connectivity between ipsilesional supplementary motor cortex (SMA)-M1 implied a worse motor function recovery (R = -0.745, P = .009). CONCLUSION: The proposed multimodal EEG/fNIRS technique demonstrates a preliminary potential for monitoring and predicting poststroke motor recovery. We expect such findings can be further validated in future study.

An EEG-fNIRS hybridization technique in the four-class classification of alzheimer's disease.

BACKGROUND: Alzheimer's disease (AD) is projected to become one of the most expensive diseases in modern history, and yet diagnostic uncertainties exist that can only be confirmed by postmortem brain examination. Machine Learning (ML) algorithms have been proposed as a feasible alternative to the diagnosis of several neurological diseases and disorders, such as AD. An ideal ML-derived diagnosis should be inexpensive and noninvasive while retaining the accuracy and versatility that make ML techniques desirable for medical applications. NEW METHODS: Two portable modalities, Electroencephalography (EEG) and functional Near-Infrared Spectroscopy (fNIRS) have been widely employed in constructing hybrid classification models to compensate for each other's weaknesses. In this study, we present a hybrid EEG-fNIRS model for classifying four classes of subjects including one healthy control (HC) group, one mild cognitive impairment (MCI) group, and, two AD patient groups. A concurrent EEG-fNIRS setup was used to record data from 29 subjects during a random digit encoding-retrieval task. EEG-derived and fNIRS-derived features were sorted using a Pearson correlation coefficient-based feature selection (PCCFS) strategy and then fed into a linear discriminant analysis (LDA) classifier to evaluate their performance. RESULTS: The hybrid EEG-fNIRS feature set was able to achieve a higher accuracy (79.31 %) by integrating their complementary properties, compared to using EEG (65.52 %) or fNIRS alone (58.62 %). Moreover, our results indicate that the right prefrontal and left parietal regions are associated with the progression of AD. COMPARISON WITH EXISTING METHODS: Our hybrid and portable system provided enhanced classification performance in multi-class classification of AD population. CONCLUSIONS: These findings suggest that hybrid EEG-fNIRS systems are a promising tool that may enhance the AD diagnosis and assessment process.

Enhancing fNIRS Analysis Using EEG Rhythmic Signatures: An EEG-Informed fNIRS Analysis Study.

Neurovascular coupling represents the relationship between changes in neuronal activity and cerebral hemodynamics. Concurrent Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) recording and integration analysis has emerged as a promising multi-modal neuroimaging approach to study the neurovascular coupling as it provides complementary properties with regard to high temporal and moderate spatial resolution of brain activity. In this study we developed an EEG-informed-fNIRS analysis framework to investigate the neuro-correlate between neuronal activity and cerebral hemodynamics by identifying specific EEG rhythmic modulations which contribute to the improvement of the fNIRS-based general linear model (GLM) analysis. Specifically, frequency-specific regressors derived from EEG were used to construct design matrices to guide the GLM analysis of the fNIRS signals collected during a hand grasp task. Our results showed that the EEG-informed fNIRS GLM analysis, especially the alpha and beta band, revealed significantly higher sensitivity and specificity in localizing the task-evoked regions compared to the canonical boxcar model, demonstrating the strong correlations between hemodynamic response and EEG rhythmic modulations. Results also indicated that analysis based on the deoxygenated hemoglobin (HbR) signal slightly outperformed the oxygenated hemoglobin (HbO)-based analysis. The findings in our study not only validate the feasibility of enhancing fNIRS GLM analysis using simultaneously recorded EEG signals, but also provide a new perspective to study the neurovascular coupling of brain activity.

Functional Network Alterations in Patients With Amnestic Mild Cognitive Impairment Characterized Using Functional Near-Infrared Spectroscopy.

Amnestic mild cognitive impairment (aMCI) is conceptualized as a cognitive disorder characterized by memory deficits. Patients with aMCI are treated as prodromal stage of Alzheimer's disease (AD) and have an increased likelihood of developing into AD. The investigation of aMCI is therefore fundamental to the early detection and intervention of AD. Growing evidence has shown that functional network alterations induced by cognition impairment can be captured by advanced neuroimaging techniques. In this study, functional near-infrared spectroscopy (fNIRS), an affordable, robust and portable neuroimaging modality, was employed to characterize the functional network in aMCI patients. FNIRS data were collected from 16 healthy controls and 16 aMCI patients using a digits verbal span task. Functional networks were constructed from temporal hemodynamic response signals. Graph-based indices were then calculated from the constructed brain networks to assess global and regional differences between the groups. Results suggested that brain networks in aMCI patients were characterized with higher integration as well as higher segregation compared to healthy controls. In addition, major regions of interest (ROIs) within frontal, temporal, precentral and parietal areas were identified to be associated with cognition impairment. Our findings validate the feasibility of utilizing fNIRS as a portable and reliable tool for the investigation of abnormal network alterations in patients with cognition decline.

Driving Fatigue Detection from EEG Using a Modified PCANet Method.

The rapid development of the automotive industry has brought great convenience to our life, which also leads to a dramatic increase in the amount of traffic accidents. A large proportion of traffic accidents were caused by driving fatigue. EEG is considered as a direct, effective, and promising modality to detect driving fatigue. In this study, we presented a novel feature extraction strategy based on a deep learning model to achieve high classification accuracy and efficiency in using EEG for driving fatigue detection. EEG signals were recorded from six healthy volunteers in a simulated driving experiment. The feature extraction strategy was developed by integrating the principal component analysis (PCA) and a deep learning model called PCA network (PCANet). In particular, the principal component analysis (PCA) was used to preprocess EEG data to reduce its dimension in order to overcome the limitation of dimension explosion caused by PCANet, making this approach feasible for EEG-based driving fatigue detection. Results demonstrated high and robust performance of the proposed modified PCANet method with classification accuracy up to 95%, which outperformed the conventional feature extraction strategies in the field. We also identified that the parietal and occipital lobes of the brain were strongly associated with driving fatigue. This is the first study, to the best of our knowledge, to practically apply the modified PCANet technique for EEG-based driving fatigue detection.

Cortical Hemodynamic Response and Connectivity Modulated by Sub-threshold High-Frequency Repetitive Transcranial Magnetic Stimulation.

Repetitive transcranial magnetic stimulation (rTMS) at sub-threshold intensity is a viable clinical strategy to enhance the sensory and motor functions of extremities by increasing or decreasing motor cortical excitability. Despite this, it remains unclear how sub-threshold rTMS modulates brain cortical excitability and connectivity. In this study, we applied functional near-infrared spectroscopy (fNIRS) to investigate the alterations in hemodynamic responses and cortical connectivity patterns that are induced by high-frequency rTMS at a sub-threshold intensity. Forty high-frequency (10 Hz) trains of rTMS at 90% resting motor threshold (RMT) were delivered through a TMS coil placed over 1-2 cm lateral from the vertex. fNIRS signals were acquired from the frontal and bilateral motor areas in healthy volunteers (n = 20) during rTMS administration and at rest. A significant reduction in oxygenated hemoglobin (HbO) concentration was observed in most defined regions of interest (ROIs) during the stimulation period (p < 0.05). Decreased functional connectivity within prefrontal areas as well as between symmetrical ROI-pairs was also observed in most participants during the stimulation (p < 0.05). Results suggest that fNIRS imaging is able to provide a reliable measure of regional cortical brain activation that advances our understanding of the manner in which sub-threshold rTMS affects cortical excitability and brain connectivity.