fNIRS-based brain-computer interfaces: a review

fNIRS experimental study on the impact of AI-synthesized familiar voices on brain neural responses

With the advancement of artificial intelligence (AI) speech synthesis technology, its application in personalized voice services and its potential role in emotional comfort have become research focal points. This study aims to explore the impact of AI-synthesized familiar and unfamiliar voices on neural responses in the brain. We utilized the GPT-SoVITS project to synthesize three types of voices: a female voice, a sweet female voice, and a maternal voice, all reading the same text. Using functional near-infrared spectroscopy (fNIRS), we monitored the changes in blood oxygen levels in the prefrontal cortex and temporal cortex of participants during listening, assessing brain activation. The experimental results showed that the AI-synthesized maternal voice significantly activated the participants' prefrontal and temporal cortices. Combined with participants' feedback, the activation of these areas may reflect multidimensional features of voice familiarity processing, including emotion, memory, and cognitive function. This finding reveals the potential applications of AI voice technology in enhancing mental health and user experience.

The association between anhedonia and prefrontal cortex activation in patients with major depression: a functional near-infrared spectroscopy study

This study investigated cerebral blood flow characteristics using functional nearinfrared spectroscopy (fNIRS) in agomelatine-treated depressed patients with anhedonia. The level of anhedonia was assessed by the Snaith Hamilton Rating Scale (SHAPS) and Montgomery Åsberg Depression Rating Scale 5-item (MADRS 5-item) score. All 84 patients were evaluated on the day of the study initiation and followed at week 1, 4 and 8 after the study initiation. Graph theory-based network analysis showed 2-back task-modulated global efficiency (adjusted B = 0.055, 95% CI = 0.043 - 0.066) and local efficiency (adjusted B = 0.066, 95% CI = 0.050 - 0.081) were significantly increased 1 week after treatment compared with the baseline. Furthermore, the increased oxy-hemoglobin (oxy-Hb) values from the baseline to the one week after treatment was positively related to the total MADRAS 5-item score reductions in the left-hemispheric orbitofrontal cortex (r = - 0.307, p = 0.005). Our findings suggest that abnormal functional connectivity over OFC may reflect the pathophysiological characteristics of anhedonia and serve as a clinical biomarker for anhedonia.

Effects of different AI-driven Chatbot feedback on learning outcomes and brain activity

Artificial intelligence (AI) driven chatbots provide instant feedback to support learning. Yet, the impacts of different feedback types on behavior and brain activation remain underexplored. We investigated how metacognitive, affective, and neutral feedback from an educational chatbot affected learning outcomes and brain activity using functional near-infrared spectroscopy. Students receiving metacognitive feedback showed higher transfer scores, greater metacognitive sensitivity, and increased brain activation in the frontopolar area and middle temporal gyrus compared to other feedback types. Such activation correlated with metacognitive sensitivity. Students receiving affective feedback showed better retention scores than those receiving neutral feedback, along with higher activation in the supramarginal gyrus. Students receiving neutral feedback exhibited higher activation in the dorsolateral prefrontal cortex than other feedback types. The machine learning model identified key brain regions that predicted transfer scores. These findings underscore the potential of diverse feedback types in enhancing learning via human-chatbot interaction, and provide neurophysiological signatures.

Simultaneous Mental Fatigue and Mental Workload Assessment With Wearable High-Density Diffuse Optical Tomography

Accurately assessing mental states-such as mental workload and fatigue- is crucial for ensuring the reliability and effectiveness of brain-computer interface (BCI)-based applications. Relying on signals from a limited brain region with low spatial resolution may fail to capture the full scope of relevant information. To address this, high-density diffuse optical tomography (HD-DOT), an emerging form of functional near-infrared spectroscopy (fNIRS) was employed in this study, which provides higher spatial resolution for hemodynamic measurements and enables the reconstruction of 3D brain images. An experiment protocol was designed to investigate both mental workload and fatigue, two critical components of cognitive state that often fluctuate concurrently in real-world scenarios. Machine learning methods were applied for subject-specific classification, achieving 95.14% mean accuracy for fatigue/non-fatigue and 97.93% for four n-back tasks using Random Forest, outperforming Support Vector Machines. These results highlight the transformative potential of HD-DOT in advancing multifaceted cognitive state assessment, paving the way for more precise, adaptable, and powerful BCI applications.

Co-localized optode-electrode design for multimodal functional near infrared spectroscopy and electroencephalography

Significance

Neuroscience of the everyday world requires continuous mobile brain imaging in real time and in ecologically valid environments, which aids in directly translating research for human benefit. Combined functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) studies have increased in demand, as the combined systems can provide great insights into cortical hemodynamics, neuronal activity, and neurovascular coupling. However, fNIRS-EEG studies remain limited in modularity and portability due to restrictions in combined cap designs, especially for high-density (HD) fNIRS measurements.

Aim

We have built and tested custom fNIRS sources that attach to electrodes without decreasing the overall modularity and portability of the probe.

Approach

To demonstrate the design's utility, we screened for any potential interference and performed a HD-fNIRS-EEG measurement with co-located opto-electrode positions during a modified Stroop task.

Results

No observable interference was present from the fNIRS source optodes in the EEG spectral analysis. The performance, fNIRS, and EEG results of the Stroop task supported the trends from previous research. We observed increased activation with both fNIRS and EEG within the regions of interest.

Conclusion

Overall, these results suggest that the co-localization method is a promising approach to multimodal imaging.

High-Density Multi-Distance fNIRS Enhances Detection of Brain Activity during a Word-Color Stroop Task

Significance

Functional Near-Infrared Spectroscopy (fNIRS) enables neuroimaging in scenarios where other modalities are less suitable, such as during motion tasks or in low-resource environments. Sparse fNIRS arrays with 30mm channel spacing are widely used but have limited spatial resolution. High-density (HD) arrays with overlapping, multi-distance channels improve sensitivity and localization but increase costs and setup times. A statistical comparison of HD and sparse arrays is needed for evaluating the benefits and trade-offs of HD arrays.

Aim

This study provides a statistical comparison of HD and sparse fNIRS performance to inform array selection in future research.

Approach

We measured prefrontal cortex (PFC) activation during congruent and incongruent Word-Color Stroop (WCS) tasks using both Sparse and HD arrays for 17 healthy adult participants, comparing dorsolateral PFC channel and image results at the group level.

Results

While both arrays detected activation in channel space during incongruent WCS, channel and image space results demonstrated superior localization and sensitivity with the HD array for all WCS.

Conclusions

Sparse channel data may suitably detect activation from cognitively demanding tasks, like incongruent WCS. However, the HD array outperformed Sparse in detecting and localizing brain activity in image space, particularly during lower cognitive load tasks, making them more suitable for neuroimaging applications.

Functional near-infrared spectroscopy for the assessment and treatment of patients with disorders of consciousness

Background

Advances in neuroimaging have significantly enhanced our understanding of brain function, providing critical insights into the diagnosis and management of disorders of consciousness (DoC). Functional near-infrared spectroscopy (fNIRS), with its real-time, portable, and noninvasive imaging capabilities, has emerged as a promising tool for evaluating functional brain activity and nonrecovery potential in DoC patients. This review explores the current applications of fNIRS in DoC research, identifies its limitations, and proposes future directions to optimize its clinical utility.

Aim

This review examines the clinical application of fNIRS in monitoring DoC. Specifically, it investigates the potential value of combining fNIRS with brain-computer interfaces (BCIs) and closed-loop neuromodulation systems for patients with DoC, aiming to elucidate mechanisms that promote neurological recovery.

Methods

A systematic analysis was conducted on 155 studies published between January 1993 and October 2024, retrieved from the Web of Science Core Collection database.

Results

Analysis of 21 eligible studies on neurological diseases involving 262 DoC patients revealed significant findings. The prefrontal cortex was the most frequently targeted brain region. fNIRS has proven crucial in assessing brain functional connectivity and activation, facilitating the diagnosis of DoC. Furthermore, fNIRS plays a pivotal role in diagnosis and treatment through its application in neuromodulation techniques such as deep brain stimulation (DBS) and spinal cord stimulation (SCS).

Conclusion

As a noninvasive, portable, and real-time neuroimaging tool, fNIRS holds significant promise for advancing the assessment and treatment of DoC. Despite limitations such as low spatial resolution and the need for standardized protocols, fNIRS has demonstrated its utility in evaluating residual brain activity, detecting covert consciousness, and monitoring therapeutic interventions. In addition to assessing consciousness levels, fNIRS offers unique advantages in tracking hemodynamic changes associated with neuroregulatory treatments, including DBS and SCS. By providing real-time feedback on cortical activation, fNIRS facilitates optimizing therapeutic strategies and supports individualized treatment planning. Continued research addressing its technical and methodological challenges will further establish fNIRS as an indispensable tool in the diagnosis, prognosis, and treatment monitoring of DoC patients.

Boy's love fans versus non-fans in the sexual identity and neural response in the digital age's young females

With the omnipresence of online social media, Boys' Love (BL) culture has found a burgeoning audience among young females. However, we know very little about the audience of this online cultural phenomena, also the potential implications of BL culture to female remain under-explored. Study 1 conducted a survey to investigate the BL audience's demography data and attitudes to homosexual ect. The results of the questionnaire analysis showed that the sexual orientation and psychological gender of the female BL audiences are more diverse. In addition, we also find the audience spend a lot of time on BL. Study 2 focused on the BL senior fans to explore the neural and behavioral response of female while looking at Boys' Love(BL) stimuli and Heterosexual love stimuli by fNIRS. Behavioral results showed that there was no main effect of reaction time and accuracy between the BL-fans and non-BL-fans. Neural results confirmed that the Oxy-Hb responses for BL-love stimuli in BL-fans was significantly lower than the non-BL-fans. In addition, the interaction effect showed that the Oxy-Hb responses was significantly higher for BL-love stimuli than for heterosexual love stimuli in non-BL-fans, and no difference was found in BL-fans. This finding, maybe along with the discovery that the more pornography a person was exposed to, the higher the brain dopamine threshold, and the subsequent weakening of the neural response to sexual stimulation. The research leads to the conclusion that long term exposed to Boys' Love may decrease the reward sensitivity to BL stimuli and weakens the brain's response of the right ventrolateral prefrontal cortex (rVLPFC) to BL stimuli.

Exploring Effects of Mental Stress with Data Augmentation and Classification Using fNIRS

Accurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data and achieving meaningful classification results remain a challenge. In this study, we employ a classification strategy to explore stress and its impact on spatial activation patterns and brain connectivity caused by the Stroop color-word task (SCWT). To improve our results and increase our dataset, we use data augmentation with a deep convolutional generative adversarial network (DCGAN). The study is carried out at two separate times of day (morning and evening) and involves 21 healthy participants. Additionally, we introduce binaural beats (BBs) stimulation to investigate its potential for stress reduction. The morning session includes a control phase with 10 SCWT trials, whereas the afternoon session is divided into three phases: stress, mitigation (with 16 Hz BB stimulation), and post-mitigation, each with 10 SCWT trials. For a comprehensive evaluation, the acquired fNIRS data are classified using a variety of machine-learning approaches. Linear discriminant analysis (LDA) showed a maximum accuracy of 60%, whereas non-augmented data classified by a convolutional neural network (CNN) provided the highest classification accuracy of 73%. Notably, after augmenting the data with DCGAN, the classification accuracy increases dramatically to 96%. In the time series data, statistically significant differences were noticed in the data before and after BB stimulation, which showed an improvement in the brain state, in line with the classification results. These findings illustrate the ability to detect changes in brain states with high accuracy using fNIRS, underline the need for larger datasets, and demonstrate that data augmentation can significantly help when data are scarce in the case of brain signals.

A Novel Recognition and Classification Approach for Motor Imagery Based on Spatio-Temporal Features

Motor imagery, as a paradigm of brain-computer interface, holds vast potential in the field of medical rehabilitation. Addressing the challenges posed by the non-stationarity and low signal-to-noise ratio of EEG signals, the effective extraction of features from motor imagery signals for accurate recognition stands as a key focus in motor imagery brain-computer interface technology. This paper proposes a motor imagery EEG signal classification model that combines functional brain networks with graph convolutional networks. First, functional brain networks are constructed using different brain functional connectivity metrics, and graph theory features are calculated to deeply analyze the characteristics of brain networks under different motor tasks. Then, the constructed functional brain networks are combined with graph convolutional networks for the classification and recognition of motor imagery tasks. The analysis based on brain functional connectivity reveals that the functional connectivity strength during the both fists task is significantly higher than that of other motor imagery tasks, and the functional connectivity strength during actual movement is generally superior to that of motor imagery tasks. In experiments conducted on the Physionet public dataset, the proposed model achieved a classification accuracy of 88.39% under multi-subject conditions, significantly outperforming traditional methods. Under single-subject conditions, the model effectively addressed the issue of individual variability, achieving an average classification accuracy of 99.31%. These results indicate that the proposed model not only exhibits excellent performance in the classification of motor imagery tasks but also provides new insights into the functional connectivity characteristics of different motor tasks and their corresponding brain regions.

Signal acquisition of brain-computer interfaces: A medical-engineering crossover perspective review

Brain-computer interface (BCI) technology represents a burgeoning interdisciplinary domain that facilitates direct communication between individuals and external devices. The efficacy of BCI systems is largely contingent upon the progress in signal acquisition methodologies. This paper endeavors to provide an exhaustive synopsis of signal acquisition technologies within the realm of BCI by scrutinizing research publications from the last ten years. Our review synthesizes insights from both clinical and engineering viewpoints, delineating a comprehensive two-dimensional framework for understanding signal acquisition in BCIs. We delineate nine discrete categories of technologies, furnishing exemplars for each and delineating the salient challenges pertinent to these modalities. This review furnishes researchers and practitioners with a broad-spectrum comprehension of the signal acquisition landscape in BCI, and deliberates on the paramount issues presently confronting the field. Prospective enhancements in BCI signal acquisition should focus on harmonizing a multitude of disciplinary perspectives. Achieving equilibrium between signal fidelity, invasiveness, biocompatibility, and other pivotal considerations is imperative. By doing so, we can propel BCI technology forward, bolstering its effectiveness, safety, and dependability, thereby contributing to an auspicious future for human-technology integration.

Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification

Purpose

In the brain-computer interface (BCI), motor imagery (MI) could be defined as the Electroencephalogram (EEG) signals through imagined movements, and ultimately enabling individuals to control external devices. However, the low signal-to-noise ratio, multiple channels and non-linearity are the essential challenges of accurate MI classification. To tackle these issues, we investigate the role of adaptive frequency bands selection and spatial-temporal feature learning in decoding motor imagery.

Methods

We propose an Adaptive Filter of Frequency Bands based Coordinate Attention Network (AFFB-CAN) to improve the performance of MI classification. Specifically, we design the AFFB to adaptively obtain the upper and lower limits of frequency bands in order to alleviate information loss caused by manual selection. Next, we propose the CAN-based network to emphasize the key brain regions and temporal segments. And we design a multi-scale module to enhance temporal context learning.

Results

The conducted experiments on the BCI Competition IV-2a and 2b datasets reveal that our approach achieves an outstanding average accuracy, kappa values, and Macro F1-Score with 0.7825, 0.7104, and 0.7486 respectively. Similarly, for the BCI Competition IV-2b dataset, the average accuracy, kappa values, and F1-Score obtained are 0.8879, 0.7427, and 0.8734, respectively.

Conclusion

The proposed AFFB-CAN method improves the performance of MI classification. In addition, our study confirms previous findings that motor imagery is mainly associated with µ and β rhythms. Moreover, we also find that γ rhythms also play an important role in MI classification.

A class alignment network based on self-attention for cross-subject EEG classification

Due to the inherent variability in EEG signals across different individuals, domain adaptation and adversarial learning strategies are being progressively utilized to develop subject-specific classification models by leveraging data from other subjects. These approaches primarily focus on domain alignment and tend to overlook the critical task-specific class boundaries. This oversight can result in weak correlation between the extracted features and categories. To address these challenges, we propose a novel model that uses the known information from multiple subjects to bolster EEG classification for an individual subject through adversarial learning strategies. Our method begins by extracting both shallow and attention-driven deep features from EEG signals. Subsequently, we employ a class discriminator to encourage the same-class features from different domains to converge while ensuring that the different-class features diverge. This is achieved using our proposed discrimination loss function, which is designed to minimize the feature distance for samples of the same class across different domains while maximizing it for those from different classes. Additionally, our model incorporates two parallel classifiers that are harmonious yet distinct and jointly contribute to decision-making. Extensive testing on two publicly available EEG datasets has validated our model's efficacy and superiority.

Hybrid Functional Near-Infrared Spectroscopy System and Electromyography for Prosthetic Knee Control

The increasing number of individuals with limb loss worldwide highlights the need for advancements in prosthetic knee technology. To improve control and quality of life, integrating brain-computer communication with motor imagery offers a promising solution. This study introduces a hybrid system that combines electromyography (EMG) and functional near-infrared spectroscopy (fNIRS) to address these limitations and enhance the control of knee movements for individuals with above-knee amputations. The study involved an experiment with nine healthy male participants, consisting of two sessions: real execution and imagined execution using motor imagery. The OpenBCI Cyton board collected EMG signals corresponding to the desired movements, while fNIRS monitored brain activity in the prefrontal and motor cortices. The analysis of the simultaneous measurement of the muscular and hemodynamic responses demonstrated that combining these data sources significantly improved the classification accuracy compared to using each dataset alone. The results showed that integrating both the EMG and fNIRS data consistently achieved a higher classification accuracy. More specifically, the Support Vector Machine performed the best during the motor imagery tasks, with an average accuracy of 49.61%, while the Linear Discriminant Analysis excelled in the real execution tasks, achieving an average accuracy of 89.67%. This research validates the feasibility of using a hybrid approach with EMG and fNIRS to enable prosthetic knee control through motor imagery, representing a significant advancement potential in prosthetic technology.

Differential Hemodynamic Responses to Motor and Tactile Imagery: Insights from Multichannel fNIRS Mapping

Tactile and motor imagery are crucial components of sensorimotor functioning and cognitive neuroscience research, yet the neural mechanisms of tactile imagery remain underexplored compared to motor imagery. This study employs multichannel functional near-infrared spectroscopy (fNIRS) combined with image reconstruction techniques to investigate the neural hemodynamics associated with tactile (TI) and motor imagery (MI). In a study of 15 healthy participants, we found that MI elicited significantly greater hemodynamic responses (HRs) in the precentral area compared to TI, suggesting the involvement of different cortical areas involved in two different types of sensorimotor mental imagery. Concurrently, the HRs in S1 and parietal areas exhibited comparable patterns in both TI and MI. During MI, both motor and somatosensory areas demonstrated comparable HRs. However, in TI, somatosensory activation was observed to be more pronounced. Our results highlight the distinctive neural profiles of motor versus tactile imagery and indicate fNIRS technique to be sensitive for this. This distinction is significant for fundamental understanding of sensorimotor integration and for developing advanced neurotechnologies, including imagery-based brain-computer interfaces (BCIs) that can differentiate between different types of mental imagery.

Graph Convolutional Network With Connectivity Uncertainty for EEG-Based Emotion Recognition

Automatic emotion recognition based on multichannel Electroencephalography (EEG) holds great potential in advancing human-computer interaction. However, several significant challenges persist in existing research on algorithmic emotion recognition. These challenges include the need for a robust model to effectively learn discriminative node attributes over long paths, the exploration of ambiguous topological information in EEG channels and effective frequency bands, and the mapping between intrinsic data qualities and provided labels. To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena. Moreover, the graph mixup technique is employed to enhance latent connected edges and mitigate noisy label issues. Furthermore, we integrate the uncertainty learning method with deep GCN weights in a one-way learning fashion, termed Connectivity Uncertainty GCN (CU-GCN). We evaluate our approach on two widely used datasets, namely SEED and SEEDIV, for emotion recognition tasks. The experimental results demonstrate the superiority of our methodology over previous methods, yielding positive and significant improvements. Ablation studies confirm the substantial contributions of each component to the overall performance.

Association of Compensatory Mechanisms in Prefrontal Cortex and Impaired Anatomical Correlates in Semantic Verbal Fluency: A Functional Near-Infrared Spectroscopy Study

OBJECTIVE

Semantic verbal fluency (SVF) engages cognitive functions such as executive function, mental flexibility, and semantic memory. Left frontal and temporal lobes, particularly the left inferior frontal gyrus (IFG), are crucial for SVF. This study investigates SVF and associated neural processing in older adults with mild SVF impairment and the relationship between structural abnormalities in the left IFG and functional activation during SVF in those individuals.

METHODS

Fifty-four elderly individuals with modest level of mild cognitive impairment whose global cognition were preserved to normal but exhibited mild SVF impairment were participated. Prefrontal oxyhemoglobin (HbO2) activation and frontal cortical thickness were collected from the participants using functional near-infrared spectroscopy (fNIRS) and brain MRI, respectively. We calculated the β coefficient of HbO2 activation induced by tasks, and performed correlation analysis between SVF induced HbO2 activation and cortical thickness in frontal areas.

RESULTS

We observed increased prefrontal activation during SVF task compared to the resting and control task. The activation distinct to SVF was identified in the midline superior and left superior prefrontal regions (p<0.05). Correlation analysis revealed an inverse relationship between SVF-specific activation and cortical thickness in the left IFG, particularly in pars triangularis (r(54)=-0.304, p=0.025).

CONCLUSION

The study contributes to understanding the relationship between reduced cortical thickness in left IFG and increased functional activity in cognitively normal individuals with mild SVF impairment, providing implications on potential compensatory mechanisms for cognitive preservation.

Decoding working-memory load duringn-back task performance from high channel fNIRS data

Objective.Functional near-infrared spectroscopy (fNIRS) can measure neural activity through blood oxygenation changes in the brain in a wearable form factor, enabling unique applications for research in and outside the lab and in practical occupational settings. fNIRS has proven capable of measuring cognitive states such as mental workload, often using machine learning (ML) based brain-computer interfaces (BCIs). To date, this research has largely relied on probes with channel counts from under ten to several hundred, although recently a new class of wearable NIRS devices featuring thousands of channels has emerged. This poses unique challenges for ML classification, as fNIRS is typically limited by few training trials which results in severely under-determined estimation problems. So far, it is not well understood how such high-resolution data is best leveraged in practical BCIs and whether state-of-the-art or better performance can be achieved.Approach.To address these questions, we propose an ML strategy to classify working-memory load that relies on spatio-temporal regularization and transfer learning from other subjects in a combination that, to our knowledge, has not been used in previous fNIRS BCIs. The approach can be interpreted as an end-to-end generalized linear model and allows for a high degree of interpretability using channel-level or cortical imaging approaches.Main results.We show that using the proposed methodology, it is possible to achieve state-of-the-art decoding performance with high-resolution fNIRS data. We also replicated several state-of-the-art approaches on our dataset of 43 participants wearing a 3198 dual-channel NIRS device while performing then-Back task and show that these existing methodologies struggle in the high-channel regime and are largely outperformed by the proposed pipeline.Significance.Our approach helps establish high-channel NIRS devices as a viable platform for state-of-the-art BCI and opens new applications using this class of headset while also enabling high-resolution model imaging and interpretation.

A multistrategy differential evolution algorithm combined with Latin hypercube sampling applied to a brain-computer interface to improve the effect of node displacement

Injection molding is a common plastic processing technique that allows melted plastic to be injected into a mold through pressure to form differently shaped plastic parts. In injection molding, in-mold electronics (IME) can include various circuit components, such as sensors, amplifiers, and filters. These components can be injected into the mold to form a whole within the melted plastic and can therefore be very easily integrated into the molded part. The brain-computer interface (BCI) is a direct connection pathway between a human or animal brain and an external device. Through BCIs, individuals can use their own brain signals to control these components, enabling more natural and intuitive interactions. In addition, brain-computer interfaces can also be used to assist in medical treatments, such as controlling prosthetic limbs or helping paralyzed patients regain mobility. Brain-computer interfaces can be realized in two ways: invasively and noninvasively, and in this paper, we adopt a noninvasive approach. First, a helmet model is designed according to head shape, and second, a printed circuit film is made to receive EEG signals and an IME injection mold for the helmet plastic parts. In the electronic film, conductive ink is printed to connect each component. However, improper parameterization during the injection molding process can lead to node displacements and residual stress changes in the molded part, which can damage the circuits in the electronic film and affect its performance. Therefore, in this paper, the use of the BCI molding process to ensure that the node displacement reaches the optimal value is studied. Second, the multistrategy differential evolutionary algorithm is used to optimize the injection molding parameters in the process of brain-computer interface formation. The relationship between the injection molding parameters and the actual target value is investigated through Latin hypercubic sampling, and the optimized parameters are compared with the target parameters to obtain the optimal parameter combination. Under the optimal parameters, the node displacement can be optimized from 0.585 to 0.027 mm, and the optimization rate can reach 95.38%. Ultimately, by detecting whether the voltage difference between the output inputs is within the permissible range, the reliability of the brain-computer interface after node displacement optimization can be evaluated.

A Knowledge-Driven Framework Discovers Brain ACtivation-Transition-Spectrum (ACTS) Features for Parkinson's Disease

Dopaminergic treatment has proved effective to Parkinson's disease (PD), but the conventional treatment assessment is human-administered and prone to intra- and inter-assessor variability. In this paper, we propose a knowledge-driven framework and discover that brain ACtivation-Transition-Spectrum (ACTS) features achieve effective quantified assessments of dopaminergic therapy in PD. Firstly, brain activities of fifty-one PD patients during clinical walking tests under the OFF and ON states (without and with dopaminergic medication) were measured with functional near-infrared spectroscopy (fNIRS). Then, brain ACTS features were formulated based on the medication-induced variations in temporal features of brain regional activation, transition features of brain hemodynamic states, and graph spectrum of brain functional connectivity. Afterwards, a prior selection algorithm was constructed based on recursive feature elimination and graph spectrum analysis for the selection of principal discriminative features. Further, linear discriminant analysis was conducted to predict the treatment-induced improvements. The results demonstrated that the proposed method decreased the misclassification probability from 42% to 16% in the evaluations of dopaminergic treatment and outperformed existing fNIRS-based methods. Therefore, the proposed method promises a quantified and objective approach for dopaminergic treatment assessment, and our brain ACTS features may serve as promising functional biomarkers for treatment evaluation.

Real-time motion artifact suppression using convolution neural networks with penalty in fNIRS

Introduction

Removing motion artifacts (MAs) from functional near-infrared spectroscopy (fNIRS) signals is crucial in practical applications, but a standard procedure is not available yet. Artificial neural networks have found applications in diverse domains, such as voice and image processing, while their utility in signal processing remains limited.

Method

In this work, we introduce an innovative neural network-based approach for online fNIRS signals processing, tailored to individual subjects and requiring minimal prior experimental data. Specifically, this approach employs one-dimensional convolutional neural networks with a penalty network (1DCNNwP), incorporating a moving window and an input data augmentation procedure. In the training process, the neural network is fed with simulated data derived from the balloon model for simulation validation and semi-simulated data for experimental validation, respectively.

Results

Visual validation underscores 1DCNNwP's capacity to effectively suppress MAs. Quantitative analysis reveals a remarkable improvement in signal-to-noise ratio by over 11.08 dB, surpassing the existing methods, including the spline-interpolation, wavelet-based, temporal derivative distribution repair with a 1 s moving window, and spline Savitzky-Goaly methods. Contrast-to-noise ratio (CNR) analysis further demonstrated 1DCNNwP's ability to restore or enhance CNRs for motionless signals. In the experiments of eight subjects, our method significantly outperformed the other approaches (except offline TDDR, t < -3.82, p < 0.01). With an average signal processing time of 0.53 ms per sample, 1DCNNwP exhibited strong potential for real-time fNIRS data processing.

Discussion

This novel univariate approach for fNIRS signal processing presents a promising avenue that requires minimal prior experimental data and adapts seamlessly to varying experimental paradigms.

Functional Near-Infrared Spectroscopy-Based Computer-Aided Diagnosis of Major Depressive Disorder Using Convolutional Neural Network with a New Channel Embedding Layer Considering Inter-Hemispheric Asymmetry in Prefrontal Hemodynamic Responses

Background

Functional near-infrared spectroscopy (fNIRS) is being extensively explored as a potential primary screening tool for major depressive disorder (MDD) because of its portability, cost-effectiveness, and low susceptibility to motion artifacts. However, the fNIRS-based computer-aided diagnosis (CAD) of MDD using deep learning methods has rarely been studied. In this study, we propose a novel deep learning framework based on a convolutional neural network (CNN) for the fNIRS-based CAD of MDD with high accuracy.

Materials and Methods

The fNIRS data of participants-48 patients with MDD and 68 healthy controls (HCs)-were obtained while they performed a Stroop task. The hemodynamic responses calculated from the preprocessed fNIRS data were used as inputs to the proposed CNN model with an ensemble CNN architecture, comprising three 1D depth-wise convolutional layers specifically designed to reflect interhemispheric asymmetry in hemodynamic responses between patients with MDD and HCs, which is known to be a distinct characteristic in previous MDD studies. The performance of the proposed model was evaluated using a leave-one-subject-out cross-validation strategy and compared with those of conventional machine learning and CNN models.

Results

The proposed model exhibited a high accuracy, sensitivity, and specificity of 84.48%, 83.33%, and 85.29%, respectively. The accuracies of conventional machine learning algorithms-shrinkage linear discriminator analysis, regularized support vector machine, EEGNet, and ShallowConvNet-were 73.28%, 74.14%, 62.93%, and 62.07%, respectively.

Conclusions

In conclusion, the proposed deep learning model can differentiate between the patients with MDD and HCs more accurately than the conventional models, demonstrating its applicability in fNIRS-based CAD systems.

Emerging Medical Technologies and Their Use in Bionic Repair and Human Augmentation

As both the proportion of older people and the length of life increases globally, a rise in age-related degenerative diseases, disability, and prolonged dependency is projected. However, more sophisticated biomedical materials, as well as an improved understanding of human disease, is forecast to revolutionize the diagnosis and treatment of conditions ranging from osteoarthritis to Alzheimer's disease as well as impact disease prevention. Another, albeit quieter, revolution is also taking place within society: human augmentation. In this context, humans seek to improve themselves, metamorphosing through self-discipline or more recently, through use of emerging medical technologies, with the goal of transcending aging and mortality. In this review, and in the pursuit of improved medical care following aging, disease, disability, or injury, we first highlight cutting-edge and emerging materials-based neuroprosthetic technologies designed to restore limb or organ function. We highlight the potential for these technologies to be utilized to augment human performance beyond the range of natural performance. We discuss and explore the growing social movement of human augmentation and the idea that it is possible and desirable to use emerging technologies to push the boundaries of what it means to be a healthy human into the realm of superhuman performance and intelligence. This potential future capability is contrasted with limitations in the right-to-repair legislation, which may create challenges for patients. Now is the time for continued discussion of the ethical strategies for research, implementation, and long-term device sustainability or repair.

Flexible circuit-based spatially aware modular optical brain imaging system for high-density measurements in natural settings

Significance

Functional near-infrared spectroscopy (fNIRS) presents an opportunity to study human brains in everyday activities and environments. However, achieving robust measurements under such dynamic conditions remains a significant challenge.

Aim

The modular optical brain imaging (MOBI) system is designed to enhance optode-to-scalp coupling and provide a real-time probe three-dimensional (3D) shape estimation to improve the use of fNIRS in everyday conditions.

Approach

The MOBI system utilizes a bendable and lightweight modular circuit-board design to enhance probe conformity to head surfaces and comfort for long-term wearability. Combined with automatic module connection recognition, the built-in orientation sensors on each module can be used to estimate optode 3D positions in real time to enable advanced tomographic data analysis and motion tracking.

Results

Optical characterization of the MOBI detector reports a noise equivalence power of 8.9 and 7.3    pW / Hz at 735 and 850 nm, respectively, with a dynamic range of 88 dB. The 3D optode shape acquisition yields an average error of 4.2 mm across 25 optodes in a phantom test compared with positions acquired from a digitizer. Results for initial in vivo validations, including a cuff occlusion and a finger-tapping test, are also provided.

Conclusions

To the best of our knowledge, the MOBI system is the first modular fNIRS system featuring fully flexible circuit boards. The self-organizing module sensor network and automatic 3D optode position acquisition, combined with lightweight modules ( 18    g / module ) and ergonomic designs, would greatly aid emerging explorations of brain function in naturalistic settings.

Interplay between cerebral and muscular activations during motor tasks: An fNIRS-sEMG study

Understanding the intricate relationship between brain activations and muscle activations during motor tasks is crucial for elucidating motor control mechanisms and designing effective rehabilitation strategies. In this study, we investigated this relationship using functional near-infrared spectroscopy (fNIRS) and surface electromyography (sEMG) technologies. Three healthy male subjects performed lower-limb motor tasks while their brain activations and muscle activations were recorded simultaneously. The fNIRS data were converted to optical densities and filtered by lowpass filter, detrending, and short-separation regression to remove artifacts. The filtered signals were fed to a general linear model with the desired hemodynamic responses (dHRFs) constructed with Balloon model and simulated physiological noises reconstructed with the parameters obtained from the spectrum analysis of baseline signals. Despite the extracted hemodynamic responses from fNIRS data, sEMG signals were lowpass and analyzed to detect muscle activations. Results revealed that cerebral activations during lateral leg flexion tasks were similar yet only partially consistent with those observed in stand-up tasks. Significant correlations between brain and muscle activations were also observed, highlighting the complex interplay between central and peripheral neural mechanisms during motor control. These findings provide valuable insights into the neural basis of motor control and have implications for developing personalized rehabilitation interventions and assistive technologies to enhance motor function in clinical populations.

Mental Fatigue Classification with High-Density Diffuse Optical Tomography: A Feasibility Study

High-Density Diffuse Optical Tomography (HD-DOT) presents as a promising tool for not only clinical use but also daily monitoring of mental states. This study employed wearable HD-DOT to evaluate mental fatigue, specifically examining the differences in functional near-infrared spectroscopy (fNIRS) data between states of low and high fatigue among healthy participants for data collection. Data processing involved filtering, channel selection, and dimensionality reduction through Uniform Manifold Approximation (UMAP) and Projection, followed by classification using Support Vector Machines (SVM). We developed two models to assess the accuracy and generalizability of our findings: one based on individually tailored models and another employing a leave-one-participant-out cross-validation strategy. We evaluated different kernel functions, resulting in various accuracy, F1 score, and Area Under the Curve (AUC) metrics. The study achieved an average accuracy of approximately 90% for participant-specific classifiers, underscoring the effectiveness of our approach to differentiate between low and high states of mental fatigue. Our analyses led to a robust model demonstrating high classification accuracy, proving its suitability and potential for real-time Brain-Computer Interface (BCI) applications.

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Optimizing spatial specificity and signal quality in fNIRS: an overview of potential challenges and possible options for improving the reliability of real-time applications

The optical brain imaging method functional near-infrared spectroscopy (fNIRS) is a promising tool for real-time applications such as neurofeedback and brain-computer interfaces. Its combination of spatial specificity and mobility makes it particularly attractive for clinical use, both at the bedside and in patients' homes. Despite these advantages, optimizing fNIRS for real-time use requires careful attention to two key aspects: ensuring good spatial specificity and maintaining high signal quality. While fNIRS detects superficial cortical brain regions, consistently and reliably targeting specific regions of interest can be challenging, particularly in studies that require repeated measurements. Variations in cap placement coupled with limited anatomical information may further reduce this accuracy. Furthermore, it is important to maintain good signal quality in real-time contexts to ensure that they reflect the true underlying brain activity. However, fNIRS signals are susceptible to contamination by cerebral and extracerebral systemic noise as well as motion artifacts. Insufficient real-time preprocessing can therefore cause the system to run on noise instead of brain activity. The aim of this review article is to help advance the progress of fNIRS-based real-time applications. It highlights the potential challenges in improving spatial specificity and signal quality, discusses possible options to overcome these challenges, and addresses further considerations relevant to real-time applications. By addressing these topics, the article aims to help improve the planning and execution of future real-time studies, thereby increasing their reliability and repeatability.

Correlation-Filter-Based Channel and Feature Selection Framework for Hybrid EEG-fNIRS BCI Applications

The proposed study is based on a feature and channel selection strategy that uses correlation filters for brain-computer interface (BCI) applications using electroencephalography (EEG)-functional near-infrared spectroscopy (fNIRS) brain imaging modalities. The proposed approach fuses the complementary information of the two modalities to train the classifier. The channels most closely correlated with brain activity are extracted using a correlation-based connectivity matrix for fNIRS and EEG separately. Furthermore, the training vector is formed through the identification and fusion of the statistical features of both modalities (i.e., slope, skewness, maximum, skewness, mean, and kurtosis). The constructed fused feature vector is passed through various filters (including ReliefF, minimum redundancy maximum relevance, chi-square test, analysis of variance, and Kruskal-Wallis filters) to remove redundant information before training. Traditional classifiers such as neural networks, support-vector machines, linear discriminant analysis, and ensembles were used for the purpose of training and testing. A publicly available dataset with motor imagery information was used for validation of the proposed approach. Our findings indicate that the proposed correlation-filter-based channel and feature selection framework significantly enhances the classification accuracy of hybrid EEG-fNIRS. The ReliefF-based filter outperformed other filters with the ensemble classifier with a high accuracy of 94.77 ± 4.26%. The statistical analysis also validated the significance (p < 0.01) of the results. A comparison of the proposed framework with the prior findings was also presented. Our results show that the proposed approach can be used in future EEG-fNIRS-based hybrid BCI applications.

Identifying Naturalistic Movies from Human Brain Activity with High-Density Diffuse Optical Tomography

Modern neuroimaging modalities, particularly functional MRI (fMRI), can decode detailed human experiences. Thousands of viewed images can be identified or classified, and sentences can be reconstructed. Decoding paradigms often leverage encoding models that reduce the stimulus space into a smaller yet generalizable feature set. However, the neuroimaging devices used for detailed decoding are non-portable, like fMRI, or invasive, like electrocorticography, excluding application in naturalistic use. Wearable, non-invasive, but lower-resolution devices such as electroencephalography and functional near-infrared spectroscopy (fNIRS) have been limited to decoding between stimuli used during training. Herein we develop and evaluate model-based decoding with high-density diffuse optical tomography (HD-DOT), a higher-resolution expansion of fNIRS with demonstrated promise as a surrogate for fMRI. Using a motion energy model of visual content, we decoded the identities of novel movie clips outside the training set with accuracy far above chance for single-trial decoding. Decoding was robust to modulations of testing time window, different training and test imaging sessions, hemodynamic contrast, and optode array density. Our results suggest that HD-DOT can translate detailed decoding into naturalistic use.

Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities

Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy in identifying intralimb movements, such as the dorsiflexion and plantar flexion of the foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize intralimb movements to facilitate the development of Brain-Computer Interface (BCI) devices for foot rehabilitation. This research involved twenty-two healthy, right-handed participants. EEG data were collected using 21 electrodes positioned over the motor cortex, while two electromyography (EMG) electrodes recorded the onset of ankle joint movements. The study focused on analyzing slow cortical potential (SCP) and sensorimotor rhythms (SMR) in alpha and beta bands from the EEG. Five key features-fourth-order Autoregressive feature, variance, waveform length, standard deviation, and permutation entropy-were extracted. A modified Recurrent Neural Network (RNN) including Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms was developed for movement recognition. These were compared against conventional machine learning algorithms, including nonlinear Support Vector Machine (SVM) and k Nearest Neighbourhood (kNN) classifiers. The performance of the proposed models was assessed using two data schemes: within-subject and across-subjects. The findings demonstrated that the GRU and LSTM models significantly outperformed traditional machine learning algorithms in recognizing different EEG signal quantities for intralimb movement. The study indicates that deep learning models, particularly GRU and LSTM, hold superior potential over standard machine learning techniques in identifying intralimb movements using EEG signals. Where the accuracies of LSTM for within and across subjects were 98.87 ± 1.80 % and 87.38 ± 0.86 % respectively. Whereas the accuracy of GRU within and across subjects were 99.18 ± 1.28 % and 86.44 ± 0.69 % respectively. This advancement could significantly benefit the development of BCI devices aimed at foot rehabilitation, suggesting a new avenue for enhancing physical therapy outcomes.

Working memory load recognition with deep learning time series classification

Working memory load (WML) is one of the widely applied signals in the areas of human-machine interaction. The precise evaluation of the WML is crucial for this kind of application. This study aims to propose a deep learning (DL) time series classification (TSC) model for inter-subject WML decoding. We used fNIRS to record the hemodynamic signals of 27 participants during visual working memory tasks. Traditional machine learning and deep time series classification algorithms were respectively used for intra-subject and inter-subject WML decoding from the collected blood oxygen signals. The intra-subject classification accuracy of LDA and SVM were 94.6% and 79.1%. Our proposed TAResnet-BiLSTM model had the highest inter-subject WML decoding accuracy, reaching 92.4%. This study provides a new idea and method for the brain-computer interface application of fNIRS in real-time WML detection.

The efficacy and methodology of using near-infrared spectroscopy to determine resting-state brain networks

Functional connectivity is a critical aspect of brain function and is essential for understanding, diagnosing, and treating neurological and psychiatric disorders. It refers to the synchronous activity between different regions of the brain, which gives rise to communication and information processing. Resting-state functional connectivity is a subarea of study that allows researchers to examine brain activity in the absence of a task or stimulus. This can provide insight into the brain's intrinsic functional architecture and help identify neural networks that are active during rest. Thus, determining functional connectivity topography is valuable both clinically and in research. Traditional methods using functional magnetic resonance imaging have proven to be effective, however, they have their limitations. In this review, we investigate the feasibility of using functional near-infrared spectroscopy (fNIRS) as a low-cost, portable alternative for measuring functional connectivity. We first establish fNIRS' ability to detect localized brain activity during task-based experiments. Next, we verify its use in resting-state studies with results showing a high degree of correspondence with resting-state functional magnetic resonance imaging (rs-fMRI). Also discussed are various data-processing methods and the validity of filtering the global signal, which is the current standard for analysis. We consider the possible origins of the global signal, if it contains pertinent neuronal information that could be of importance in better understanding neuronal networks, and what we believe is the best method of approaching signal analysis and regression.

Alterations in brain functional connectivity in patients with mild cognitive impairment: A systematic review and meta-analysis of functional near-infrared spectroscopy studies

Emerging evidences suggest that cognitive deficits in individuals with mild cognitive impairment (MCI) are associated with disruptions in brain functional connectivity (FC). This systematic review and meta-analysis aimed to comprehensively evaluate alterations in FC between MCI individuals and healthy control (HC) using functional near-infrared spectroscopy (fNIRS). Thirteen studies were included in qualitative analysis, with two studies synthesized for quantitative meta-analysis. Overall, MCI patients exhibited reduced resting-state FC, predominantly in the prefrontal, parietal, and occipital cortex. Meta-analysis of two studies revealed a significant reduction in resting-state FC from the right prefrontal to right occipital cortex (standardized mean difference [SMD] = -.56; p < .001), left prefrontal to left occipital cortex (SMD = -.68; p < .001), and right prefrontal to left occipital cortex (SMD = -.53; p < .001) in MCI patients compared to HC. During naming animal-walking task, MCI patients exhibited enhanced FC in the prefrontal, motor, and occipital cortex, whereas a decrease in FC was observed in the right prefrontal to left prefrontal cortex during calculating-walking task. In working memory tasks, MCI predominantly showed increased FC in the medial and left prefrontal cortex. However, a decreased in prefrontal FC and a shifted in distribution from the left to the right prefrontal cortex were noted in MCI patients during a verbal frequency task. In conclusion, fNIRS effectively identified abnormalities in FC between MCI and HC, indicating disrupted FC as potential markers for the early detection of MCI. Future studies should investigate the use of task- and region-specific FC alterations as a sensitive biomarker for MCI.

Repetitive Transcranial Alternating Current Stimulation to Improve Working Memory: An EEG-fNIRS Study

Transcranial electrical stimulation has demonstrated the potential to enhance cognitive functions such as working memory, learning capacity, and attentional allocation. Recently, it was shown that periodic stimulation within a specific duration could augment the human brain's neuroplasticity. This study investigates the effects of repetitive transcranial alternating current stimulation (tACS; 1 mA, 5 Hz, 2 min duration) on cognitive function, functional connectivity, and topographic changes using both electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS). Fifteen healthy subjects were recruited to measure brain activity in the pre-, during-, and post-stimulation sessions under tACS and sham stimulation conditions. Fourteen trials of working memory tasks and eight repetitions of tACS/sham stimulation with a 1-minute intersession interval were applied to the frontal cortex of the participants. The working memory score, EEG band-wise powers, EEG topography, concentration changes of oxygenated hemoglobin, and functional connectivity (FC) were individually analyzed to quantify the behavioral and neurophysiological effects of tACS. Our results indicate that tACS increases: i) behavioral scores (i.e., 15.08, ) and EEG band-wise powers (i.e., theta and beta bands) compared to the sham stimulation condition, ii) FC of both EEG-fNIRS signals, especially in the large-scale brain network communication and interhemispheric connections, and iii) the hemodynamic response in comparison to the pre-stimulation session and the sham condition. Conclusively, the repetitive theta-band tACS stimulation improves the working memory capacity regarding behavioral and neuroplasticity perspectives. Additionally, the proposed fNIRS biomarkers (mean, slope), EEG band-wise powers, and FC can be used as neuro-feedback indices for closed-loop brain stimulation.

Subject-specific information enhances spatial accuracy of high-density diffuse optical tomography

Functional near-infrared spectroscopy (fNIRS) is a widely used imaging method for mapping brain activation based on cerebral hemodynamics. The accurate quantification of cortical activation using fNIRS data is highly dependent on the ability to correctly localize the positions of light sources and photodetectors on the scalp surface. Variations in head size and shape across participants greatly impact the precise locations of these optodes and consequently, the regions of the cortical surface being reached. Such variations can therefore influence the conclusions drawn in NIRS studies that attempt to explore specific cortical regions. In order to preserve the spatial identity of each NIRS channel, subject-specific differences in NIRS array registration must be considered. Using high-density diffuse optical tomography (HD-DOT), we have demonstrated the inter-subject variability of the same HD-DOT array applied to ten participants recorded in the resting state. We have also compared three-dimensional image reconstruction results obtained using subject-specific positioning information to those obtained using generic optode locations. To mitigate the error introduced by using generic information for all participants, photogrammetry was used to identify specific optode locations per-participant. The present work demonstrates the large variation between subjects in terms of which cortical parcels are sampled by equivalent channels in the HD-DOT array. In particular, motor cortex recordings suffered from the largest optode localization errors, with a median localization error of 27.4 mm between generic and subject-specific optodes, leading to large differences in parcel sensitivity. These results illustrate the importance of collecting subject-specific optode locations for all wearable NIRS experiments, in order to perform accurate group-level analysis using cortical parcellation.

Unleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface

In this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements to increase the number of control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, a well-known task in fNIRS and fMRI studies, but limited to left/right or few fingers. Twenty-four right-handed participants performed the individual finger-tapping task. Data were recorded by using sixteen sources and detectors placed over the motor cortex according to the 10-10 international system. The event's average oxygenated Δ HbO and deoxygenated Δ HbR hemoglobin data were utilized as features to assess the performance of diverse machine learning (ML) models in a challenging multi-class classification setting. These methods include LDA, QDA, MNLR, XGBoost, and RF. A new DL-based model named "Hemo-Net" has been proposed which consists of multiple parallel convolution layers with different filters to extract the features. This paper aims to explore the efficacy of using fNRIS along with ML/DL methods in a multi-class classification task. Complex models like RF, XGBoost, and Hemo-Net produce relatively higher test set accuracy when compared to LDA, MNLR, and QDA. Hemo-Net has depicted a superior performance achieving the highest test set accuracy of 76%, however, in this work, we do not aim at improving the accuracies of models rather we are interested in exploring if fNIRS has the neural signatures to help modern ML/DL methods in multi-class classification which can lead to applications like brain-computer interfaces. Multi-class classification of fine anatomical movements, such as individual finger movements, is difficult to classify with fNIRS data. Traditional ML models like MNLR and LDA show inferior performance compared to the ensemble-based methods of RF and XGBoost. DL-based method Hemo-Net outperforms all methods evaluated in this study and demonstrates a promising future for fNIRS-based BCI applications.

fNIRS Dataset During Complex Scene Analysis

When analyzing complex scenes, humans often focus their attention on an object at a particular spatial location. The ability to decode the attended spatial location would facilitate brain computer interfaces for complex scene analysis (CSA). Here, we investigated capability of functional near-infrared spectroscopy (fNIRS) to decode audio-visual spatial attention in the presence of competing stimuli from multiple locations. We targeted dorsal frontoparietal network including frontal eye field (FEF) and intra-parietal sulcus (IPS) as well as superior temporal gyrus/planum temporal (STG/PT). They all were shown in previous functional magnetic resonance imaging (fMRI) studies to be activated by auditory, visual, or audio-visual spatial tasks. To date, fNIRS has not been applied to decode auditory and visual-spatial attention during CSA, and thus, no such dataset exists yet. This report provides an open-access fNIRS dataset that can be used to develop, test, and compare machine learning algorithms for classifying attended locations based on the fNIRS signals on a single trial basis.

Beta bursts question the ruling power for brain-computer interfaces

Objective: Current efforts to build reliable brain-computer interfaces (BCI) span multiple axes from hardware, to software, to more sophisticated experimental protocols, and personalized approaches. However, despite these abundant efforts, there is still room for significant improvement. We argue that a rather overlooked direction lies in linking BCI protocols with recent advances in fundamental neuroscience.Approach: In light of these advances, and particularly the characterization of the burst-like nature of beta frequency band activity and the diversity of beta bursts, we revisit the role of beta activity in 'left vs. right hand' motor imagery (MI) tasks. Current decoding approaches for such tasks take advantage of the fact that MI generates time-locked changes in induced power in the sensorimotor cortex and rely on band-passed power changes in single or multiple channels. Although little is known about the dynamics of beta burst activity during MI, we hypothesized that beta bursts should be modulated in a way analogous to their activity during performance of real upper limb movements.Main results and Significance: We show that classification features based on patterns of beta burst modulations yield decoding results that are equivalent to or better than typically used beta power across multiple open electroencephalography datasets, thus providing insights into the specificity of these bio-markers.

Technical note: High-efficient and wireless transcranial ultrasound excitation based on electromagnetic acoustic transducer

BACKGROUND

The generation of transcranial ultrasound is usually based on the piezoelectric effect, so it is necessary to attach transducers around the skull. However, the skull will cause serious attenuation and scattering of ultrasound, which makes it particularly difficult for transcranial ultrasound imaging and modulation.

PURPOSE

In transcranial ultrasound imaging, there is significant attenuation and scattering of ultrasound waves by the skull bone. To mitigate this influence and enable precise imaging and high-efficient transcranial ultrasound for specific patients (such as stroke patients who already require craniotomy as part of their surgical care), this paper proposes to use EMAT to excite metal plates placed inside the skull based on the excellent penetration characteristics of EM waves into the skull, generating ultrasound signals, which can completely avoid the influence of skull on ultrasound transmission.

METHODS

Based on an efficient wireless transcranial ultrasound experimental platform, we first verified that the skull would not affect the propagation of electromagnetic waves generated by EMAT. In addition, the distribution of the transcranial sound field generated by EMAT was measured.

RESULTS

EMAT can generate 1.0 MHz ultrasound by wireless excitation of a 0.1 mm thick copper plate through an adult skull with a thickness of ∼1 cm, and the frequency and amplitude of the generated ultrasound are not affected by the skull. The results indicated that the electromagnetic waves successfully penetrated the skull, with a recorded strength of approximately 2 mV. We also found that the ultrasound signals generated by the EMAT probe through the skull remained unaffected, measuring around 2 mV. In addition, the measurement of the transcranial sound field distribution (80*50 mm2 ) generated by EMAT shows that compared with the traditional extracranial ultrasound generation method, the sound field distribution generated by the wireless excitation of the intracranial copper plate based on EAMT is no longer affected by the uneven and irregular skull.

CONCLUSION

Our experiments involved validating the penetration capabilities of electromagnetic waves utilizing the EMAT probe through a 7 (5+2) mm thick organic glass plate and a real human skull ranging from 8 to 15 mm in thickness. The efficient and wireless transcranial ultrasound excitation proposed in this paper may be possible for transcranial ultrasound imaging and therapy.

Machines, mathematics, and modules: the potential to provide real-time metrics for pain under anesthesia

The brain-based assessments under anesthesia have provided the ability to evaluate pain/nociception during surgery and the potential to prevent long-term evolution of chronic pain. Prior studies have shown that the functional near-infrared spectroscopy (fNIRS)-measured changes in cortical regions such as the primary somatosensory and the polar frontal cortices show consistent response to evoked and ongoing pain in awake, sedated, and anesthetized patients. We take this basic approach and integrate it into a potential framework that could provide real-time measures of pain/nociception during the peri-surgical period. This application could have significant implications for providing analgesia during surgery, a practice that currently lacks quantitative evidence to guide patient tailored pain management. Through a simple readout of "pain" or "no pain," the proposed system could diminish or eliminate levels of intraoperative, early post-operative, and potentially, the transition to chronic post-surgical pain. The system, when validated, could also be applied to measures of analgesic efficacy in the clinic.

Learning based motion artifacts processing in fNIRS: a mini review

This paper provides a concise review of learning-based motion artifacts (MA) processing methods in functional near-infrared spectroscopy (fNIRS), highlighting the challenges of maintaining optimal contact during subject movement, which can lead to MA and compromise data integrity. Traditional strategies often result in reduced reliability of the hemodynamic response and statistical power. Recognizing the limited number of studies focusing on learning-based MA removal, we examine 315 studies, identifying seven pertinent to our focus area. We discuss the current landscape of learning-based MA correction methods and highlight research gaps. Noting the absence of standard evaluation metrics for quality assessment of MA correction, we suggest a novel framework, integrating signal and model quality considerations and employing metrics like ΔSignal-to-Noise Ratio (ΔSNR), confusion matrix, and Mean Squared Error. This work aims to facilitate the application of learning-based methodologies to fNIRS and improve the accuracy and reliability of neurovascular studies.

Feasibility of local interpretable model-agnostic explanations (LIME) algorithm as an effective and interpretable feature selection method: comparative fNIRS study

Many feature selection methods have been evaluated in functional near-infrared spectroscopy (fNIRS)-related studies. The local interpretable model-agnostic explanation (LIME) algorithm is a feature selection method for fNIRS datasets that has not yet been validated; the demand for its validation is increasing. To this end, we assessed the feature selection performance of LIME for fNIRS datasets in terms of classification accuracy. A comparative analysis was conducted for the benchmark (classification accuracy obtained without applying any feature selection method), LIME, two filter-based methods (minimum-redundancy maximum-relevance and t-test), and one wrapper-based method (sequential forward selection). To ensure the fairness and reliability of the performance evaluation, several open-access fNIRS datasets were used. The analysis revealed that LIME greatly outperformed the other feature selection methods in most cases and could achieve a statistically significantly better classification accuracy than that of the benchmark methods. These findings implied the effectiveness of LIME as a feature selection approach for fNIRS datasets.

Deep neural network to differentiate internet gaming disorder from healthy controls during stop-signal task: a multichannel near-infrared spectroscopy study

Internet Gaming Disorder (IGD), as one of worldwide mental health issues, leads to negative effects on physical and mental health and has attracted public attention. Most studies on IGD are based on screening scales and subjective judgments of doctors, without objective quantitative assessment. However, public understanding of internet gaming disorder lacks objectivity. Therefore, the researches on internet gaming disorder still have many limitations. In this paper, a stop-signal task (SST) was designed to assess inhibitory control in patients with IGD based on prefrontal functional near-infrared spectroscopy (fNIRS). According to the scale, the subjects were divided into health and gaming disorder. A total of 40 subjects (24 internet gaming disorders; 16 healthy controls) signals were used for deep learning-based classification. The seven algorithms used for classification and comparison were deep learning algorithms (DL) and machine learning algorithms (ML), with four and three algorithms in each category, respectively. After applying hold-out method, the performance of the model was verified by accuracy. DL models outperformed traditional ML algorithms. Furthermore, the classification accuracy of the two-dimensional convolution neural network (2D-CNN) was 87.5% among all models. This was the highest accuracy out of all models that were tested. The 2D-CNN was able to outperform the other models due to its ability to learn complex patterns in data. This makes it well-suited for image classification tasks. The findings suggested that a 2D-CNN model is an effective approach for predicting internet gaming disorder. The results show that this is a reliable method with high accuracy to identify patients with IGD and demonstrate that the use of fNIRS to facilitate the development of IGD diagnosis has great potential.

Deep Learning Based Walking Tasks Classification in Older Adults Using fNIRS

Decline in gait features is common in older adults and an indicator of increased risk of disability, morbidity, and mortality. Under dual task walking (DTW) conditions, further degradation in the performance of both the gait and the secondary cognitive task were found in older adults which were significantly correlated to falls history. Cortical control of gait, specifically in the pre-frontal cortex (PFC) as measured by functional near infrared spectroscopy (fNIRS), during DTW in older adults has recently been studied. However, the automatic classification of differences in cognitive activations under single and dual task gait conditions has not been extensively studied yet. In this paper, by considering single task walking (STW) as a lower attentional walking state and DTW as a higher attentional walking state, we aimed to formulate this as an automatic detection of low and high attentional walking states and leverage deep learning methods to perform their classification. We conduct analysis on the data samples which reveals the characteristics on the difference between HbO2 and Hb values that are subsequently used as additional features. We perform feature engineering to formulate the fNIRS features as a 3-channel image and apply various image processing techniques for data augmentation to enhance the performance of deep learning models. Experimental results show that pre-trained deep learning models that are fine-tuned using the collected fNIRS dataset together with gender and cognitive status information can achieve around 81% classification accuracy which is about 10% higher than the traditional machine learning algorithms. We present additional sensitivity metrics such as confusion matrix, precision and F1 score, as well as accuracy on two-way classification between condition pairings. We further performed an extensive ablation study to evaluate factors such as the voxel locations, channels of input images, zero-paddings and pre-training of deep learning model on their contribution or impact to the classification task. Results showed that using pre-trained model, all the voxel locations, and HbO2 - Hb as the third channel of the input image can achieve the best classification accuracy.

Hierarchical Classification Strategy for Mitigating the Impact of The Presence of Pain in fNIRS-based BCIs

Brain computer interfaces (BCIs) can find applications in assistive systems for patients who experience conditions that impede their motor abilities. A BCI uses signals acquired from the brain to control external devices. As physical pain influences cortical signals, the presence of pain can negatively impact the performance of the BCI. In this work, we propose a strategy to mitigate this negative impact. Cortical signals are acquired from test subjects while they performed two mental arithmetic tasks, in the presence and the absence of painful stimuli. The task of the BCI is to reliably classify the two mental arithmetic tasks from the cortical recordings, irrespective of the presence or the absence of pain. We propose to do this classification, hierarchically, in two levels. In the first level, the data is classified into those captured in the presence and the absence of pain. Depending on the results of the classification from the first level, in the second level, the BCI performs the classification of tasks using a classifier trained either in the presence or the absence of pain. A 1-dimensional convolutional neural network (1D-CNN) is used for classification at both levels. It is observed that using this hierarchical strategy, the BCI is able to classify the tasks with an accuracy greater than 90%, irrespective of the presence or the absence of pain. Given that the presence of physical pain has shown previously to reduce the classification accuracy of a BCI to almost chance levels, this mitigation strategy will be a significant step towards enhancing the performance of BCIs when they are used in assistive systems for patients.

The Effects of Different Brain Regions on fNIRS-based Task-state Detection in Speech Imagery

Brain-computer interface (BCI) based on speech imagery can decode users' verbal intent and help people with motor disabilities communicate naturally. Functional near-infrared spectroscopy (fNIRS) is a commonly used brain signal acquisition method. Asynchronous BCI can response to control commands at any time, which provides great convenience for users. Task state detection, defined as identifying whether user starts or continues covertly articulating, plays an important role in speech imagery BCIs. To better distinguish task state from idle state during speech imagery, this work used fNIRS signals from different brain regions to study the effects of different brain regions on task state detection accuracy. The imagined tonal syllables included four lexical tones and four vowels in Mandarin Chinese. The brain regions that were measured included Broca's area, Wernicke's area, Superior temporal cortex and Motor cortex. Task state detection accuracies of imagining tonal monosyllables with four different tones were analyzed. The average accuracy of four speech imagery tasks based on the whole brain was 0.67 and it was close to 0.69, which was the average accuracy based on Broca's area. The accuracies of Broca's area and the whole brain were significantly higher than those of other brain regions. The findings of this work demonstrated that using a few channels of Broca's area could result in a similar task state detection accuracy to that using all the channels of the brain. Moreover, it was discovered that speech imagery with tone 2/3 tasks yielded higher task state detection accuracy than speech imagery with other tones.

Decoupling brain activations of muscle-caused activations and mental intention-cause activations using the general linear model: A functional near-infrared spectroscopy study

Integrating a brain-computer interface into a lower-limb medical rehabilitation assistive device can enhance rehabilitation efficiency. The latest research in the field focuses on the decoding performance of different motions. However, the difference between muscle-caused primitive activation and mental intention-caused activation has not been fully investigated. Thus, our study tried to decouple these two kinds of cerebral activation using a general linear model (GLM). Nine healthy and right-handed subjects were recruited for a two-section experiment. They were asked to extend or flex their knees while seated in the first section of the experiment or standing in the second section. Functional near-infrared spectroscopy (fNIR) was adopted to monitor their hemodynamic changes. Two groups of paradigms (one for circle-wise analysis, the other for full-section analysis) were constructed from the experimental paradigm. Each group consisted of three (the first intention, the second intention, and the muscle activation). The constructed paradigms were fed to the Balloon model for six desired hemodynamic responses (dHRFs). The regressor of GLM consisted of three dHRFs and the corresponding motion artifacts and drifts. The simulated physiological noises were included in the structured background matrix. The results showed that all subjects had similar cerebral activation patterns for the intention to extend or flex knees. The activation during musclecaused activation was less intense than that caused by both intentions. This finding can help further research on more efficient motion intention detection and the possibility of multiple motions decoding.

Transformer Based Cross-Subject Mental Workload Classification Using FNIRS for Real-World Application

Mental state monitoring is a hot topic especially in neurorehabilitation, skill training, etc, for which the functional near-infrared spectroscopy (fNIRS) has been suggested to be used, and fewer detection channels and cross-subject performance are usually required for real-world application. To this goal, we propose a transformer-based method for cross-subject mental workload classification using fewer channels of fNIRS. Firstly, the input fNIRS signals in a window are divided into patches in the temporal order and transformed into embeddings, to which a classification token and learnable position embeddings are added. Then, a transformer encoder is used to learn the long-range dependencies among the embeddings, of which the output classification token is sent to a multilayer perceptron (MLP) head. Mental workload classification results can be represented by the outputs of the MLP head. Finally, comparison experiments were conducted on the open-access fNIRS2MW dataset. The results show that, the proposed method can outperform previous methods in cross-subject classification accuracy, and relatively efficient computation can be obtained.