Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain–computer interface (BCI). EEG signals require a large number of channels in the acquisition process, which hinders its application in practice. How to select the optimal channel subset without a serious impact on the classification performance is an urgent problem to be solved in the field of BCIs. This article proposes an end-to-end deep learning framework, called EEG channel active inference neural network (EEG-ARNN), which is based on graph convolutional neural networks (GCN) to fully exploit the correlation of signals in the temporal and spatial domains. Two channel selection methods, i.e., edge-selection (ES) and aggregation-selection (AS), are proposed to select a specified number of optimal channels automatically. Two publicly available BCI Competition IV 2a (BCICIV 2a) dataset and PhysioNet dataset and a self-collected dataset (TJU dataset) are used to evaluate the performance of the proposed method. Experimental results reveal that the proposed method outperforms state-of-the-art methods in terms of both classification accuracy and robustness. Using only a small number of channels, we obtain a classification performance similar to that of using all channels. Finally, the association between selected channels and activated brain areas is analyzed, which is important to reveal the working state of brain during MI.

Objective . Blood flow is one such available observable promoting a wealth of physiological insight both individually and in combination with other metrics. Approach . Near-infrared diffuse correlation spectroscopy (DCS) and, to a lesser extent, diffuse correlation tomography (DCT), have increasingly received interest over the past decade as noninvasive methods for tissue blood flow measurements and imaging. DCS/DCT offers several attractive features for tissue blood flow measurements/imaging such as noninvasiveness, portability, high temporal resolution, and relatively large penetration depth (up to several centimeters). Main results . This review first introduces the basic principle and instrumentation of DCS/DCT, followed by presenting clinical application examples of DCS/DCT for the diagnosis and therapeutic monitoring of diseases in a variety of organs/tissues including brain, skeletal muscle, and tumor. Significance . Clinical study results demonstrate technical versatility of DCS/DCT in providing important information for disease diagnosis and intervention monitoring.

Classification of electroencephalogram-based motor imagery (MI-EEG) tasks raises a big challenge in the design and development of brain-computer interfaces (BCIs). In view of the characteristics of nonstationarity, time-variability, and individual diversity of EEG signals, a deep learning framework termed SSD-SE-convolutional neural network (CNN) is proposed for MI-EEG classification. The framework consists of three parts: 1) the sparse spectrotemporal decomposition (SSD) algorithm is proposed for feature extraction, overcoming the drawbacks of conventional time-frequency analysis methods and enhancing the robustness to noise; 2) a CNN is constructed to fully exploit the time-frequency features, thus outperforming traditional classification methods both in terms of accuracy and kappa value; and 3) the squeeze-and-excitation (SE) blocks are adopted to adaptively recalibrate channelwise feature responses, which further improves the overall performance and offers a compelling classification solution for MI-EEG applications. Experimental results on two datasets reveal that the proposed framework outperforms state-of-the-art methods in terms of both classification quality and robustness. The advantages of SSD-SE-CNN include high accuracy, high efficiency, and robustness to cross-trial and cross-session variations, making it an ideal candidate for long-term MI-EEG applications.

Cupping therapy has been used in traditional Chinese medicine for thousands of years to relieve muscle pain/tendency/fatigue and to cure or reduce symbols of other diseases. However, its therapeutic effect is sparsely interpreted in the language of modern physiology. To objectively evaluate its therapeutic effect, we focused on dry cupping treatment and utilized near-infrared spectroscopy (NIRS) to assess the concentration change in oxy-hemoglobin ([HbO₂]), deoxy-hemoglobin ([Hb]), and blood volume in the course of cupping therapy over 13 volunteers on the infraspinatus muscle, where is usually applied for shoulder pains. Both a prominent drop in [Hb] and a significant elevation in [HbO₂] in the tissue surrounding the cupping site were observed during both cupping and post-treatment, manifesting the enhancement of oxygen uptake. This resulting promotion indicates potential positive therapeutic effect of cupping therapy in hemodynamics for facilitating muscular functions.

Extinction coefficient (ε) is a critical parameter for quantification of oxy-, deoxy-, and total-hemoglobin concentrations (Δ[HbO₂], Δ[Hb], Δ[tHb]) from optical measurements of Near-infrared spectroscopy (NIRS). There are several different ε data sets which were frequently used in NIRS quantification. A previous study reported that even a small variation in ε could cause a significant difference in hemodynamic measurements. Apparently the selection of an optimal ε data set is important for NIRS. We conducted oxygen-state-varied and blood-concentration-varied model experiments with 57 human blood samples to mimic tissue hemodynamic variations. Seven reported ε data sets were evaluated by comparisons between quantifications and assumed values. We found that the Moaveni et al (1970)’ ε data set was the optimal one, the NIRS quantification varied significantly among different ε data sets and parameter Δ[tHb] was most sensitive to ε data sets selection.

Objective. Modern motor imagery (MI)-based brain computer interface systems often entail a large number of electroencephalogram (EEG) recording channels. However, irrelevant or highly correlated channels would diminish the discriminatory ability, thus reducing the control capability of external devices. How to optimally select channels and extract associated features remains a big challenge. This study aims to propose and validate a deep learning-based approach to automatically recognize two different MI states by selecting the relevant EEG channels. Approach. In this work, we make use of a sparse squeeze-and-excitation module to extract the weights of EEG channels based on their contribution to MI classification, by which an automatic channel selection (ACS) strategy is developed. Further, we propose a convolutional neural network to fully exploit the time-frequency features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Main results. We execute the experiments using EEG signals recorded at MI where 25 healthy subjects performed MI movements of the right hand and feet to generate motor commands. An average accuracy of 87.2 ± 5.0 % ( m e a n ± s t d ) is obtained, providing a 37.3% improvement with respect to a state-of-the-art channel selection approach. Significance. The proposed ACS method has been found to be significantly advantageous compared to the typical approach of using a fixed channel configuration. This work shows that fewer EEG channels not only reduces computational complexity but also improves the MI classification performance. The proposed method selects EEG channels related to hand and feet movement, which paves the way to real-time and more natural interfaces between the patient and the robotic device.