Invasive Brain-computer Interface Research Articles

Data augmentation for invasive brain–computer interfaces based on stereo-electroencephalography (SEEG)

Objective. Deep learning is increasingly used for brain–computer interfaces (BCIs). However, the quantity of available data is sparse, especially for invasive BCIs. Data augmentation (DA) methods, such as generative models, can help to address this sparseness. However, all the existing studies on brain signals were based on convolutional neural networks and ignored the temporal dependence. This paper attempted to enhance generative models by capturing the temporal relationship from a time-series perspective. Approach. A conditional generative network (conditional transformer-based generative adversarial network (cTGAN)) based on the transformer model was proposed. The proposed method was tested using a stereo-electroencephalography (SEEG) dataset which was recorded from eight epileptic patients performing five different movements. Three other commonly used DA methods were also implemented: noise injection (NI), variational autoencoder (VAE), and conditional Wasserstein generative adversarial network with gradient penalty (cWGANGP). Using the proposed method, the artificial SEEG data was generated, and several metrics were used to compare the data quality, including visual inspection, cosine similarity (CS), Jensen–Shannon distance (JSD), and the effect on the performance of a deep learning-based classifier. Main results. Both the proposed cTGAN and the cWGANGP methods were able to generate realistic data, while NI and VAE outputted inferior samples when visualized as raw sequences and in a lower dimensional space. The cTGAN generated the best samples in terms of CS and JSD and outperformed cWGANGP significantly in enhancing the performance of a deep learning-based classifier (each of them yielding a significant improvement of 6% and 3.4%, respectively). Significance. This is the first time that DA methods have been applied to invasive BCIs based on SEEG. In addition, this study demonstrated the advantages of the model that preserves the temporal dependence from a time-series perspective.

Channel Selection for Stereo-electroencephalography (SEEG)-based Invasive Brain-Computer Interfaces using Deep Learning Methods.

Brain-computer interfaces (BCIs) can enable direct communication with assistive devices by recording and decoding signals from the brain. To achieve high performance, many electrodes will be used, such as the recently developed invasive BCIs with channel numbers up to hundreds or even thousands. For those high-throughput BCIs, channel selection is important to reduce signal redundancy and invasiveness while maintaining decoding performance. However, such endeavour is rarely reported for invasive BCIs, especially those using deep learning methods. Two deep learning-based methods, referred to as Gumbel and STG, were proposed in this paper. They were evaluated using the Stereo-electroencephalography (SEEG) signals, and compared with three other methods, including manual selection, mutual information-based method (MI), and all channels (all channels without selection). The task is to classify the SEEG signals into five movements using channels selected by each method. When 10 channels were selected, the mean classification accuracies using Gumbel, STG (referred to as STG-10), manual selection, and MI selection were 65%, 60%, 60%, and 47%, respectively, whilst the accuracy was 59% using all channels (no selection). In addition, an investigation of the selected channels showed that Gumbel and STG have successfully identified the pre-central and post-central areas, which are closely related to motor control. Both Gumbel and STG successfully selected the informative channels in SEEG recordings while maintaining decoding accuracy. This study enables future high-throughput BCIs using deep learning methods, to identify useful channels and reduce computing and wireless transmission pressure.

A Review of Motor Brain-Computer Interfaces Using Intracranial Electroencephalography Based on Surface Electrodes and Depth Electrodes.

Brain-computer interfaces (BCIs) provide a communication interface between the brain and external devices and have the potential to restore communication and control in patients with neurological injury or disease. For the invasive BCIs, most studies recruited participants from hospitals requiring invasive device implantation. Three widely used clinical invasive devices that have the potential for BCIs applications include surface electrodes used in electrocorticography (ECoG) and depth electrodes used in Stereo-electroencephalography (SEEG) and deep brain stimulation (DBS). This review focused on BCIs research using surface (ECoG) and depth electrodes (including SEEG, and DBS electrodes) for movement decoding on human subjects. Unlike previous reviews, the findings presented here are from the perspective of the decoding target or task. In detail, five tasks will be considered, consisting of the kinematic decoding, kinetic decoding,identification of body parts, dexterous hand decoding, and motion intention decoding. The typical studies are surveyed and analyzed. The reviewed literature demonstrated a distributed motor-related network that spanned multiple brain regions. Comparison between surface and depth studies demonstrated that richer information can be obtained using surface electrodes. With regard to the decoding algorithms, deep learning exhibited superior performance using raw signals than traditional machine learning algorithms. Despite the promising achievement made by the open-loop BCIs, closed-loop BCIs with sensory feedback are still in their early stage, and the chronic implantation of both ECoG surface and depth electrodes has not been thoroughly evaluated.

為侵入性腦機介面技術進行倫理辯護

LANGUAGE NOTE | Document text in Chinese; abstract also in English.
 The idea that invasive brain–computer interface technology is dangerous is debatable. This technology requires ethical justification, recognizing the coexistence of their benefits and risks. The newly formed professional consensus in China illustrates that it is possible to develop forward-looking and binding ethical guidelines through multidisciplinary argumentation and stakeholder consultation. Invasive brain–computer interfaces need not be limited to the smallest scope of application. Invasive brain–computer interfaces for healthy people and for enhancement purposes will provide technical and ethical options for future human society. Therefore, research into invasive brain–computer interfaces should not be prohibited. Rather, we must be alert to the risky possibility of research and development on brain–computer interfaces becoming entirely driven by business interests and controlled by capital. Furthermore, Chinese Taoist wisdom does not necessarily reject this technology.

腦機介面的風險與受益權衡——評《為什麼侵入性腦機介面技術是危險的》

LANGUAGE NOTE | Document text in Chinese; abstract also in English.
 Brain–computer interface (BCI) and artificial intelligence (AI) technologies are the most high-profile and disruptive technologies of our time. Professor Zhenming Zhai presents a broad and informative argument for why invasive BCIs are dangerous, fully addressing the emerging issues and challenges caused by BCI and AI technologies. In the field of biomedical research involving human subjects, conducting a reasonable and scientific assessment of the risks and benefits of BCIs is a complex, challenging, and continuous process. In the new world of man–computer symbiosis, we should not focus only to the evolution of technology itself, but also reflect on the balance from within ourselves as humans. We should think carefully, discern wisely and act earnestly.

前言：回應腦機介面技術的倫理挑戰

LANGUAGE NOTE | Document text in Chinese; abstract also in English.
 This issue of the journal delves into the ethical implications of Brain-Computer Interface (BCI) technology, featuring two thematic papers: “The Ethics of Thinking with Machines: Brain-Computer Interfaces in the Era of Artificial Intelligence” by David M. Lyreskog, Hazem Zohny, Ilina Singh, and Julian Savulescu, and ‘Why Invasive Brain-Computer Interface Technology is Dangerous’ by Zhai Zhenming. Additionally, the journal includes 19 commentary essays that respond to these papers. The authors highlight the immense potential benefits offered by this technology while acknowledging the substantial risks and uncertainties inherent in them, emphasizing the need for a thorough ethical examination. (Abstract taken from first paragraph of document)

Monitoring Alzheimer’s disease via ultraweak photon emission

In an innovative experiment, we detected ultraweak photon emission (UPE) from the hippocampus of male rat brains and found significant correlations between Alzheimer's disease (AD), memory decline, oxidative stress, and UPE intensity. These findings may open up novel methods for screening, detecting, diagnosing, and classifying neurodegenerative diseases, particularly AD. The study suggests that UPE from the brain's neural tissue can serve as a valuable indicator. It also proposes the development of a minimally invasive brain-computer interface (BCI) photonic chip for monitoring and diagnosing AD, offering high spatiotemporal resolution of brain activity. The study used a rodent model of sporadic AD, demonstrating that STZ-induced sAD resulted in increased hippocampal UPE, which was associated with oxidative stress. Treatment with donepezil reduced UPE and improved oxidative stress. These findings support the potential utility of UPE as a screening and diagnostic tool for AD and other neurodegenerative diseases.

Endovascular Brain-Computer Interfaces in Poststroke Paralysis.

Stroke is a leading cause of paralysis, most frequently affecting the upper limbs and vocal folds. Despite recent advances in care, stroke recovery invariably reaches a plateau, after which there are permanent neurological impairments. Implantable brain-computer interface devices offer the potential to bypass permanent neurological lesions. They function by (1) recording neural activity, (2) decoding the neural signal occurring in response to volitional motor intentions, and (3) generating digital control signals that may be used to control external devices. While brain-computer interface technology has the potential to revolutionize neurological care, clinical translation has been limited. Endovascular arrays present a novel form of minimally invasive brain-computer interface devices that have been deployed in human subjects during early feasibility studies. This article provides an overview of endovascular brain-computer interface devices and critically evaluates the patient with stroke as an implant candidate. Future opportunities are mapped, along with the challenges arising when decoding neural activity following infarction. Limitations arise when considering intracerebral hemorrhage and motor cortex lesions; however, future directions are outlined that aim to address these challenges.

Optimizing Future Advanced BCIs: Using WDA to Identify Potential Pain Points in BCI Systems

Brain-computer interfaces (BCIs) are a rapidly developing technology with the potential for a wide range of applications, yet the technology and its possible risks are poorly understood. The aim of this study was to develop and analyse an abstraction hierarchy model of a hypothetical, advanced invasive BCI system lifecycle to identify potential design lifecycle risks. Ten subject matter experts participated in a workshop to validate a BCI lifecycle abstraction hierarchy, which was subsequently analysed using the Sociotechnical Systems-Design Toolkit (STS-DT) prompts. The analysis identified the system purpose of generating wealth for companies and shareholders conflicted with other system purposes relating to health and wellbeing. Findings also identified poorly supported system functions, such as the regulation of BCI technologies, and potentially unreliable system objects. In conclusion, it is recommended that the identified issues be addressed through a sociotechnical systems approach focusing on joint optimisation across the system.

Hydrogel electrodes with conductive and substrate-adhesive layers for noninvasive long-term EEG acquisition

Noninvasive brain–computer interfaces (BCIs) show great potential in applications including sleep monitoring, fatigue alerts, neurofeedback training, etc. While noninvasive BCIs do not impose any procedural risk to users (as opposed to invasive BCIs), the acquisition of high-quality electroencephalograms (EEGs) in the long term has been challenging due to the limitations of current electrodes. Herein, we developed a semidry double-layer hydrogel electrode that not only records EEG signals at a resolution comparable to that of wet electrodes but is also able to withstand up to 12 h of continuous EEG acquisition. The electrode comprises dual hydrogel layers: a conductive layer that features high conductivity, low skin-contact impedance, and high robustness; and an adhesive layer that can bond to glass or plastic substrates to reduce motion artifacts in wearing conditions. Water retention in the hydrogel is stable, and the measured skin-contact impedance of the hydrogel electrode is comparable to that of wet electrodes (conductive paste) and drastically lower than that of dry electrodes (metal pin). Cytotoxicity and skin irritation tests show that the hydrogel electrode has excellent biocompatibility. Finally, the developed hydrogel electrode was evaluated in both N170 and P300 event-related potential (ERP) tests on human volunteers. The hydrogel electrode captured the expected ERP waveforms in both the N170 and P300 tests, showing similarities in the waveforms generated by wet electrodes. In contrast, dry electrodes fail to detect the triggered potential due to low signal quality. In addition, our hydrogel electrode can acquire EEG for up to 12 h and is ready for recycled use (7-day tests). Altogether, the results suggest that our semidry double-layer hydrogel electrodes are able to detect ERPs in the long term in an easy-to-use fashion, potentially opening up numerous applications in real-life scenarios for noninvasive BCI.

Motor decoding from the posterior parietal cortex using deep neural networks

Objective. Motor decoding is crucial to translate the neural activity for brain-computer interfaces (BCIs) and provides information on how motor states are encoded in the brain. Deep neural networks (DNNs) are emerging as promising neural decoders. Nevertheless, it is still unclear how different DNNs perform in different motor decoding problems and scenarios, and which network could be a good candidate for invasive BCIs. Approach. Fully-connected, convolutional, and recurrent neural networks (FCNNs, CNNs, RNNs) were designed and applied to decode motor states from neurons recorded from V6A area in the posterior parietal cortex (PPC) of macaques. Three motor tasks were considered, involving reaching and reach-to-grasping (the latter under two illumination conditions). DNNs decoded nine reaching endpoints in 3D space or five grip types using a sliding window approach within the trial course. To evaluate decoders simulating a broad variety of scenarios, the performance was also analyzed while artificially reducing the number of recorded neurons and trials, and while performing transfer learning from one task to another. Finally, the accuracy time course was used to analyze V6A motor encoding. Main results. DNNs outperformed a classic Naïve Bayes classifier, and CNNs additionally outperformed XGBoost and Support Vector Machine classifiers across the motor decoding problems. CNNs resulted the top-performing DNNs when using less neurons and trials, and task-to-task transfer learning improved performance especially in the low data regime. Lastly, V6A neurons encoded reaching and reach-to-grasping properties even from action planning, with the encoding of grip properties occurring later, closer to movement execution, and appearing weaker in darkness. Significance. Results suggest that CNNs are effective candidates to realize neural decoders for invasive BCIs in humans from PPC recordings also reducing BCI calibration times (transfer learning), and that a CNN-based data-driven analysis may provide insights about the encoding properties and the functional roles of brain regions.

Identifying risk controls for future advanced brain-computer interfaces: A prospective risk assessment approach using work domain analysis

Brain-computer interface (BCI) technologies are progressing rapidly and may eventually be implemented widely within society, yet their risks have arguably not yet been comprehensively identified, nor understood. This study analysed an anticipated invasive BCI system lifecycle to identify the individual, organisational, and societal risks associated with BCIs, and controls that could be used to mitigate or eliminate these risks. A BCI system lifecycle work domain analysis model was developed and validated with 10 subject matter experts. The model was subsequently used to undertake a systems thinking-based risk assessment approach to identify risks that could emerge when functions are either undertaken sub-optimally or not undertaken at all. Eighteen broad risk themes were identified that could negatively impact the BCI system lifecycle in a variety of unique ways, while a larger number of controls for these risks were also identified. The most concerning risks included inadequate regulation of BCI technologies and inadequate training of BCI stakeholders, such as users and clinicians. In addition to specifying a practical set of risk controls to inform BCI device design, manufacture, adoption, and utilisation, the results demonstrate the complexity involved in managing BCI risks and suggests that a system-wide coordinated response is required. Future research is required to evaluate the comprehensiveness of the identified risks and the practicality of implementing the risk controls.

Application of ECoG and Electrode in BCI

The brain-computer interface (BCI) is a new technology that connects a computer or other electronic devices to the brains of humans, animals, or even brain cell cultures. It creates a link between the brain and technology so that messages can be sent immediately. It does not rely on the muscles and peripheral nerves that generally aid in the transmission of brain information. It is widely used in rehabilitation medicine, artificial intelligence, neuroscience, and other fields. Nowadays, with the development of neuroimaging technology, brain imaging technologies recording activities on different scales have been emerging. Electrocorticography (ECoG), which is involved in semi-invasive BCI and depth electrode, which is involved in invasive BCI, has greatly promoted the development of BCI. This paper, through a method of literature review, provides general perspectives on the application of ECoG and depth electrode in BCI; describes the advantages and disadvantages of ECoG and depth electrode; and finally discusses chances for further research. Representative research findings regarding ECoG and depth electrodes in recent years were reviewed. In summary, though ECoG and depth electrode still have some limitations, their importance in the future is undisputed.

The Development of Piezoelectric Inchworm Actuator Clamped With Magnetorheological Elastomer and Its Potential Application in Brain–Computer Interface Implantation

The piezoelectric inchworm actuator with high-positioning accuracy and large output force is a potential device to implant microelectrode in the invasive brain–computer interface (BCI). However, the traditional piezoelectric inchworm actuator adopts multichannel electrical control signals from external equipment and rigid-to-rigid friction contact to drive, resulting in complex control and uneven friction. To solve the above problems, in this article, magnetorheological elastomer (MRE) is first proposed as the clamping material of the piezoelectric inchworm actuator. An MRE–capillary–cover sandwich structure is adopted to achieve rigid-to-elastomeric clamping. The driving and clamping actions of the actuator are controlled by two cam mechanisms mounted on the same shaft, and a battery can feed the actuator. A kinetic model is established to analyze and predict the actuator motion. Several crucial clamping parameters are explored, and the performance experiments are conducted to evaluate actuator characteristics. A verification experiment is carried out to prove the feasibility of the microelectrode implantation in the pig brain (0.6% agarose gel). The actuator can reach the maximum velocity of 1250.4 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">μ</i> m/s and the maximum output force of 420 mN; in the forward/backward motion, the minimum step is 0.5837/0.5912 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">μ</i> m, and the repeatability is 0.0465/0.0469 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">μ</i> m; thus, the actuator has great application potential in BCI.

Modulating Brain Activity with Invasive Brain-Computer Interface: A Narrative Review.

Brain-computer interface (BCI) can be used as a real-time bidirectional information gateway between the brain and machines. In particular, rapid progress in invasive BCI, propelled by recent developments in electrode materials, miniature and power-efficient electronics, and neural signal decoding technologies has attracted wide attention. In this review, we first introduce the concepts of neuronal signal decoding and encoding that are fundamental for information exchanges in BCI. Then, we review the history and recent advances in invasive BCI, particularly through studies using neural signals for controlling external devices on one hand, and modulating brain activity on the other hand. Specifically, regarding modulating brain activity, we focus on two types of techniques, applying electrical stimulation to cortical and deep brain tissues, respectively. Finally, we discuss the related ethical issues concerning the clinical application of this emerging technology.

Brain-Computer interface control of stepping from invasive electrocorticography upper-limb motor imagery in a patient with quadriplegia.

Introduction: Most spinal cord injuries (SCI) result in lower extremities paralysis, thus diminishing ambulation. Using brain-computer interfaces (BCI), patients may regain leg control using neural signals that actuate assistive devices. Here, we present a case of a subject with cervical SCI with an implanted electrocorticography (ECoG) device and determined whether the system is capable of motor-imagery-initiated walking in an assistive ambulator. Methods: A 24-year-old male subject with cervical SCI (C5 ASIA A) was implanted before the study with an ECoG sensing device over the sensorimotor hand region of the brain. The subject used motor-imagery (MI) to train decoders to classify sensorimotor rhythms. Fifteen sessions of closed-loop trials followed in which the subject ambulated for one hour on a robotic-assisted weight-supported treadmill one to three times per week. We evaluated the stability of the best-performing decoder over time to initiate walking on the treadmill by decoding upper-limb (UL) MI. Results: An online bagged trees classifier performed best with an accuracy of 84.15% averaged across 9 weeks. Decoder accuracy remained stable following throughout closed-loop data collection. Discussion: These results demonstrate that decoding UL MI is a feasible control signal for use in lower-limb motor control. Invasive BCI systems designed for upper-extremity motor control can be extended for controlling systems beyond upper extremity control alone. Importantly, the decoders used were able to use the invasive signal over several weeks to accurately classify MI from the invasive signal. More work is needed to determine the long-term consequence between UL MI and the resulting lower-limb control.

A survey on encoding and decoding technology of non-invasive brain-computer interface

A survey on encoding and decoding technology of non-invasive brain-computer interface

Recent Progress in Wearable Brain-Computer Interface (BCI) Devices Based on Electroencephalogram (EEG) for Medical Applications: A Review.

Importance: Brain-computer interface (BCI) decodes and converts brain signals into machine instructions to interoperate with the external world. However, limited by the implantation risks of invasive BCIs and the operational complexity of conventional noninvasive BCIs, applications of BCIs are mainly used in laboratory or clinical environments, which are not conducive to the daily use of BCI devices. With the increasing demand for intelligent medical care, the development of wearable BCI systems is necessary. Highlights: Based on the scalp-electroencephalogram (EEG), forehead-EEG, and ear-EEG, the state-of-the-art wearable BCI devices for disease management and patient assistance are reviewed. This paper focuses on the EEG acquisition equipment of the novel wearable BCI devices and summarizes the development direction of wearable EEG-based BCI devices. Conclusions: BCI devices play an essential role in the medical field. This review briefly summarizes novel wearable EEG-based BCIs applied in the medical field and the latest progress in related technologies, emphasizing its potential to help doctors, patients, and caregivers better understand and utilize BCI devices.

Research advances in non-invasive brain-computer interface control strategies

Brain-computer interface (BCI) can establish a direct communications pathway between the human brain and the external devices, which is independent of peripheral nerves and muscles. Compared with invasive BCI, non-invasive BCI has the advantages of low cost, low risk, and ease of operation. In recent years, using non-invasive BCI technology to control devices has gradually evolved into a new type of human-computer interaction manner. Moreover, the control strategy for BCI is an essential component of this manner. First, this study introduced how the brain control techniques were developed and classified. Second, the basic characteristics of direct and shared control strategies were thoroughly explained. And then the benefits and drawbacks of these two strategies were compared and further analyzed. Finally, the development direction and application prospects for non-invasive brain control strategies were suggested.

Improving the Effectiveness of Learning with the Help of Neurocomputer Interface

The article considers modern technologies for reading signals from the human brain and nervous system and selects the optimal technology to improve the efficiency of adult learning with the help of a neurocomputer interface. Existing brain-computer interfaces (BCI) technologies can be divided into invasive and non-invasive. The first, invasive BCIs, are neuroimplants in certain parts of the brain that work on the basis of electrocorticography (ECOG) or intracranial EEG (iEEG) technology and do not require deep intervention in brain structures; or another invasive BCIs, based on intracortical recording technology using implants with electrodes placed in brain closer to the signal source, and required more complicate operation. The second, non-invasive BCI, reads signals from the brain and nervous system and is based on electroencephalogram (EEG). Compared to invasive BCIs with their more accurate signal, transcranial BCIs communicate with the brain through the skull bones, muscles, and all tissues. Their use does not require intervention in the human body. To increase the effectiveness of training, there was chosen a physiotherapeutic method of transcranial electrical stimulation (TES) in combination with a braincomputer interface based on electroencephalography (EEG), as the most accessible non-invasive method of exposure and feedback due to BCI without known side effects to mental functions and personality. The use of brain-computer interfaces, in particular transcranial electrical stimulation in combination with electroencephalography, increases cognitive abilities in learning, including multitasking. This method can also be used to increase the effectiveness of human assimilation of the necessary new digital environments and is used not only for training complex professions, but also for the masses. Side effects on higher mental functions and personality have not been sufficiently studied to recommend or avoid the use of neurocomputer interfaces for widespread use in education.