Thought-based interaction: Same data, same methods, different results?

Restoration of communication in people with complete motor paralysis-a condition called complete locked-in state (CLIS)-is one of the greatest challenges of brain-computer interface (BCI) research. New findings have recently been presented that bring us one step closer to this goal. However, the validity of the evidence has been questioned: independent reanalysis of the same data yielded significantly different results. Reasons for the failure to replicate the findings must be of a methodological nature. What is the best practice to ensure that results are stringent and conclusive and analyses replicable? Confirmation bias and the counterintuitive nature of probability may lead to an overly optimistic interpretation of new evidence. Lack of detail complicates replicability.

EEG Oscillations Are Modulated in Different Behavior-Related Networks during Rhythmic Finger Movements.

Sequencing and timing of body movements are essential to perform motoric tasks. In this study, we investigate the temporal relation between cortical oscillations and human motor behavior (i.e., rhythmic finger movements). High-density EEG recordings were used for source imaging based on individual anatomy. We separated sustained and movement phase-related EEG source amplitudes based on the actual finger movements recorded by a data glove. Sustained amplitude modulations in the contralateral hand area show decrease for α (10-12 Hz) and ß (18-24 Hz), but increase for high γ (60-80 Hz) frequencies during the entire movement period. Additionally, we found movement phase-related amplitudes, which resembled the flexion and extension sequence of the fingers. Especially for faster movement cadences, movement phase-related amplitudes included high ß (24-30 Hz) frequencies in prefrontal areas. Interestingly, the spectral profiles and source patterns of movement phase-related amplitudes differed from sustained activities, suggesting that they represent different frequency-specific large-scale networks. First, networks were signified by the sustained element, which statically modulate their synchrony levels during continuous movements. These networks may upregulate neuronal excitability in brain regions specific to the limb, in this study the right hand area. Second, movement phase-related networks, which modulate their synchrony in relation to the movement sequence. We suggest that these frequency-specific networks are associated with distinct functions, including top-down control, sensorimotor prediction, and integration. The separation of different large-scale networks, we applied in this work, improves the interpretation of EEG sources in relation to human motor behavior. SIGNIFICANCE STATEMENT: EEG recordings provide high temporal resolution suitable to relate cortical oscillations to actual movements. Investigating EEG sources during rhythmic finger movements, we distinguish sustained from movement phase-related amplitude modulations. We separate these two EEG source elements motivated by our previous findings in gait. Here, we found two types of large-scale networks, representing the right fingers in distinction from the time sequence of the movements. These findings suggest that EEG source amplitudes reconstructed in a cortical patch are the superposition of these simultaneously present network activities. Separating these frequency-specific networks is relevant for studying function and possible dysfunction of the cortical sensorimotor system in humans as well as to provide more advanced features for brain-computer interfaces.

High and low gamma EEG oscillations in central sensorimotor areas are conversely modulated during the human gait cycle.

Investigating human brain function is essential to develop models of cortical involvement during walking. Such models could advance the analysis of motor impairments following brain injuries (e.g., stroke) and may lead to novel rehabilitation approaches. In this work, we applied high-density EEG source imaging based on individual anatomy to enable neuroimaging during walking. To minimize the impact of muscular influence on EEG recordings we introduce a novel artifact correction method based on spectral decomposition. High γ oscillations (>60Hz) were previously reported to play an important role in motor control. Here, we investigate high γ amplitudes while focusing on two different aspects of a walking experiment, namely the fact that a person walks and the rhythmicity of walking. We found that high γ amplitudes (60-80Hz), located focally in central sensorimotor areas, were significantly increased during walking compared to standing. Moreover, high γ (70-90Hz) amplitudes in the same areas are modulated in relation to the gait cycle. Since the spectral peaks of high γ amplitude increase and modulation do not match, it is plausible that these two high γ elements represent different frequency-specific network interactions. Interestingly, we found high γ (70-90Hz) amplitudes to be coupled to low γ (24-40Hz) amplitudes, which both are modulated in relation to the gait cycle but conversely to each other. In summary, our work is a further step towards modeling cortical involvement during human upright walking.

Level of participation in robotic-assisted treadmill walking modulates midline sensorimotor EEG rhythms in able-bodied subjects.

In robot assisted gait training, a pattern of human locomotion is executed repetitively with the intention to restore the motor programs associated with walking. Several studies showed that active contribution to the movement is critical for the encoding of motor memory. We propose to use brain monitoring techniques during gait training to encourage active participation in the movement. We investigated the spectral patterns in the electroencephalogram (EEG) that are related to active and passive robot assisted gait. Fourteen healthy participants were considered. Infomax independent component analysis separated the EEG into independent components representing brain, muscle, and eye movement activity, as well as other artifacts. An equivalent current dipole was calculated for each independent component. Independent components were clustered across participants based on their anatomical position and frequency spectra. Four clusters were identified in the sensorimotor cortices that accounted for differences between active and passive walking or showed activity related to the gait cycle. We show that in central midline areas the mu (8-12 Hz) and beta (18-21 Hz) rhythms are suppressed during active compared to passive walking. These changes are statistically significant: mu (F(1, 13)=11.2 p ≤ 0.01) and beta (F(1, 13)=7.7, p ≤ 0.05). We also show that these differences depend on the gait cycle phases. We provide first evidence of modulations of the gamma rhythm in the band 25 to 40 Hz, localized in central midline areas related to the phases of the gait cycle. We observed a trend (F(1, 8)=11.03, p ≤ 0.06) for suppressed low gamma rhythm when comparing active and passive walking. Additionally we found significant suppressions of the mu (F(1, 11)=20.1 p ≤ 0.01), beta (F(1, 11)=11.3 p ≤ 0.05) and gamma (F(1, 11)=4.9 p ≤ 0.05) rhythms near C3 (in the right hand area of the primary motor cortex) during phases of active vs. passive robot assisted walking. To our knowledge this is the first study showing EEG analysis during robot assisted walking. We provide evidence for significant differences in cortical activation between active and passive robot assisted gait. Our findings may help to define appropriate features for single trial detection of active participation in gait training. This work is a further step toward the evaluation of brain monitoring techniques and brain-computer interface technologies for improving gait rehabilitation therapies in a top-down approach.

A Machine Learning-Based Holistic Approach to Predict the Clinical Course of Patients within the Alzheimer's Disease Spectrum.

BACKGROUND: Alzheimer's disease (AD) is a neurodegenerative condition driven by multifactorial etiology. Mild cognitive impairment (MCI) is a transitional condition between healthy aging and dementia. No reliable biomarkers are available to predict the conversion from MCI to AD. OBJECTIVE: To evaluate the use of machine learning (ML) on a wealth of data offered by the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Alzheimer's Disease Metabolomics Consortium (ADMC) database in the prediction of the MCI to AD conversion. METHODS: We implemented an ML-based Random Forest (RF) algorithm to predict conversion from MCI to AD. Data related to the study population (587 MCI subjects) were analyzed by RF as separate or combined features and assessed for classification power. Four classes of variables were considered: neuropsychological test scores, AD-related cerebrospinal fluid (CSF) biomarkers, peripheral biomarkers, and structural magnetic resonance imaging (MRI) variables. RESULTS: The ML-based algorithm exhibited 86% accuracy in predicting the AD conversion of MCI subjects. When assessing the features that helped the most, neuropsychological test scores, MRI data, and CSF biomarkers were the most relevant in the MCI to AD prediction. Peripheral parameters were effective when employed in association with neuropsychological test scores. Age and sex differences modulated the prediction accuracy. AD conversion was more effectively predicted in females and younger subjects. CONCLUSION: Our findings support the notion that AD-related neurodegenerative processes result from the concerted activity of multiple pathological mechanisms and factors that act inside and outside the brain and are dynamically affected by age and sex.

ECoG Beta Suppression and Modulation During Finger Extension and Flexion.

Neural oscillations originate predominantly from interacting cortical neurons and consequently reflect aspects of cortical information processing. However, their functional role is not yet fully understood and their interpretation is debatable. Amplitude modulations (AMs) in alpha (8-12 Hz), beta (13-30 Hz), and high gamma (70-150 Hz) band in invasive electrocorticogram (ECoG) and non-invasive electroencephalogram (EEG) signals change with behavior. Alpha and beta band AMs are typically suppressed (desynchronized) during motor behavior, while high gamma AMs highly correlate with the behavior. These two phenomena are successfully used for functional brain mapping and brain-computer interface (BCI) applications. Recent research found movement-phase related AMs (MPA) also in high beta/low gamma (24-40 Hz) EEG rhythms. These MPAs were found by separating the suppressed AMs into sustained and dynamic components. Sustained AM components are those with frequencies that are lower than the motor behavior. Dynamic components those with frequencies higher than the behavior. In this paper, we study ECoG beta/low gamma band (12-30 Hz/30-42 Hz) AM during repetitive finger movements addressing the question whether or not MPAs can be found in ECoG beta band. Indeed, MPA in the 12-18 Hz and 18-24 Hz band were found. This additional information may lead to further improvements in ECoG-based prediction and reconstruction of motor behavior by combining high gamma AM and beta band MPA.

Classification of contralateral and ipsilateral finger movements for electrocorticographic brain-computer interfaces.

Electrocorticography (ECoG) offers a powerful and versatile platform for developing brain-computer interfaces; it avoids the risks of brain-invasive methods such as intracortical implants while providing significantly higher signal-to-noise ratio than noninvasive techniques such as electroencephalography. The authors demonstrate that both contra- and ipsilateral finger movements can be discriminated from ECoG signals recorded from a single brain hemisphere. The ECoG activation patterns over sensorimotor areas for contra- and ipsilateral movements were found to overlap to a large degree in the recorded hemisphere. Ipsilateral movements, however, produced less pronounced activity compared with contralateral movements. The authors also found that single-trial classification of movements could be improved by selecting patient-specific frequency components in high-frequency bands (> 50 Hz). Their discovery that ipsilateral hand movements can be discriminated from ECoG signals from a single hemisphere has important implications for neurorehabilitation, suggesting in particular the possibility of regaining ipsilateral movement control using signals from an intact hemisphere after damage to the other hemisphere.

Brain-computer communication: motivation, aim, and impact of exploring a virtual apartment.

The step away from a synchronized or cue-based brain-computer interface (BCI) and from laboratory conditions towards real world applications is very important and crucial in BCI research. This work shows that ten naive subjects can be trained in a synchronous paradigm within three sessions to navigate freely through a virtual apartment, whereby at every junction the subjects could decide by their own, how they wanted to explore the virtual environment (VE). This virtual apartment was designed similar to a real world application, with a goal-oriented task, a high mental workload, and a variable decision period for the subject. All subjects were able to perform long and stable motor imagery over a minimum time of 2 s. Using only three electroencephalogram (EEG) channels to analyze these imaginations, we were able to convert them into navigation commands. Additionally, it could be demonstrated that motivation is a very crucial factor in BCI research; motivated subjects perform much better than unmotivated ones.

Study of discriminant analysis applied to motor imagery bipolar data.

We present a study of linear, quadratic and regularized discriminant analysis (RDA) applied to motor imagery data of three subjects. The aim of the work was to find out which classifier can separate better these two-class motor imagery data: linear, quadratic or some function in between the linear and quadratic solutions. Discriminant analysis methods were tested with two different feature extraction techniques, adaptive autoregressive parameters and logarithmic band power estimates, which are commonly used in brain-computer interface research. Differences in classification accuracy of the classifiers were found when using different amounts of data; if a small amount was available, the best classifier was linear discriminant analysis (LDA) and if enough data were available all three classifiers performed very similar. This suggests that the effort needed to find regularizing parameters for RDA can be avoided by using LDA.

Heading for new shores! Overcoming pitfalls in BCI design.

Research in brain-computer interfaces has achieved impressive progress towards implementing assistive technologies for restoration or substitution of lost motor capabilities, as well as supporting technologies for able-bodied subjects. Notwithstanding this progress, effective translation of these interfaces from proof-of concept prototypes into reliable applications remains elusive. As a matter of fact, most of the current BCI systems cannot be used independently for long periods of time by their intended end-users. Multiple factors that impair achieving this goal have already been identified. However, it is not clear how do they affect the overall BCI performance or how they should be tackled. This is worsened by the publication bias where only positive results are disseminated, preventing the research community from learning from its errors. This paper is the result of a workshop held at the 6th International BCI meeting in Asilomar. We summarize here the discussion on concrete research avenues and guidelines that may help overcoming common pitfalls and make BCIs become a useful alternative communication device.

Workshops of the Sixth International Brain-Computer Interface Meeting: brain-computer interfaces past, present, and future.

The Sixth International Brain-Computer Interface (BCI) Meeting was held 30 May-3 June 2016 at the Asilomar Conference Grounds, Pacific Grove, California, USA. The conference included 28 workshops covering topics in BCI and brain-machine interface research. Topics included BCI for specific populations or applications, advancing BCI research through use of specific signals or technological advances, and translational and commercial issues to bring both implanted and non-invasive BCIs to market. BCI research is growing and expanding in the breadth of its applications, the depth of knowledge it can produce, and the practical benefit it can provide both for those with physical impairments and the general public. Here we provide summaries of each workshop, illustrating the breadth and depth of BCI research and highlighting important issues and calls for action to support future research and development.

Motor imagery and EEG-based control of spelling devices and neuroprostheses.

A brain-computer interface (BCI) transforms signals originating from the human brain into commands that can control devices or applications. With this, a BCI provides a new non-muscular communication channel, which can be used to assist patients who have highly compromised motor functions. The Graz-BCI uses motor imagery and associated oscillatory EEG signals from the sensorimotor cortex for device control. As a result of research in the past 15 years, the classification of ERD/ERS patterns in single EEG trials during motor execution and motor imagery forms the basis of this sensorimotor-rhythm controlled BCI. The major frequency bands of cortical oscillations considered here are the 8-13 and 15-30 Hz bands. This chapter describes the basic methods used in Graz-BCI research and outlines possible clinical applications.

Steady-state somatosensory evoked potentials: suitable brain signals for brain-computer interfaces?

One of the main issues in designing a brain-computer interface (BCI) is to find brain patterns, which could easily be detected. One of these pattern is the steady-state evoked potential (SSEP). SSEPs induced through the visual sense have already been used for brain-computer communication. In this work, a BCI system is introduced based on steady-state somatosensory evoked potentials (SSSEPs). Transducers have been used for the stimulation of both index fingers using tactile stimulation in the "resonance"-like frequency range of the somatosensory system. Four subjects participated in the experiments and were trained to modulate induced SSSEPs. Two of them learned to modify the patterns in order to set up a BCI with an accuracy of between 70% and 80%. Results presented in this work give evidence that it is possible to set up a BCI which is based on SSSEPs.

BCI meeting 2005--workshop on technology: hardware and software.

This paper describes the outcome of discussions held during the Third International BCI Meeting at a workshop to review and evaluate the current state of BCI-related hardware and software. Technical requirements and current technologies, standardization procedures and future trends are covered. The main conclusion was recognition of the need to focus technical requirements on the users' needs and the need for consistent standards in BCI research.

Online control of a brain-computer interface using phase synchronization.

Currently, almost all brain-computer interfaces (BCIs) ignore the relationship between phases of electroencephalographic signals detected from different recording sites (i.e., electrodes). The vast majority of BCI systems rely on feature vectors derived from e.g., bandpower or univariate adaptive autoregressive (AAR) parameters. However, ample evidence suggests that additional information is obtained by quantifying the relationship between signals of single electrodes, which might provide innovative features for future BCI systems. This paper investigates one method to extract the degree of phase synchronization between two electroencephalogram (EEG) signals by calculating the so-called phase locking value (PLV). In our offline study, several PLV-based features were acquired and the optimal feature set was selected for each subject individually by a feature selection algorithm. The online sessions with three trained subjects revealed that all subjects were able to control three mental states (motor imagery of left hand, right hand, and foot, respectively) with single-trial accuracies between 60% and 66.7% (33% would be expected by chance) throughout the whole session.

Brain-computer interfaces for control of neuroprostheses: from synchronous to asynchronous mode of operation.

Transferring a brain-computer interface (BCI) from the laboratory environment into real world applications is directly related to the problem of identifying user intentions from brain signals without any additional information in real time. From the perspective of signal processing, the BCI has to have an uncued or asynchronous design. Based on the results of two clinical applications, where 'thought' control of neuroprostheses based on movement imagery in tetraplegic patients with a high spinal cord injury has been established, the general steps from a synchronous or cue-guided BCI to an internally driven asynchronous brain-switch are discussed. The future potential of BCI methods for various control purposes, especially for functional rehabilitation of tetraplegics using neuroprosthetics, is outlined.

Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear classifier.

There is general agreement in the brain-computer interface (BCI) community that although non-linear classifiers can provide better results in some cases, linear classifiers are preferable. Particularly, as non-linear classifiers often involve a number of parameters that must be carefully chosen. However, new non-linear classifiers were developed over the last decade. One of them is the random forest (RF) classifier. Although popular in other fields of science, RFs are not common in BCI research. In this work, we address three open questions regarding RFs in sensorimotor rhythm (SMR) BCIs: parametrization, online applicability, and performance compared to regularized linear discriminant analysis (LDA). We found that the performance of RF is constant over a large range of parameter values. We demonstrate - for the first time - that RFs are applicable online in SMR-BCIs. Further, we show in an offline BCI simulation that RFs statistically significantly outperform regularized LDA by about 3%. These results confirm that RFs are practical and convenient non-linear classifiers for SMR-BCIs. Taking into account further properties of RFs, such as independence from feature distributions, maximum margin behavior, multiclass and advanced data mining capabilities, we argue that RFs should be taken into consideration for future BCIs.

Imagery of motor actions: differential effects of kinesthetic and visual-motor mode of imagery in single-trial EEG.

Single-trial motor imagery classification is an integral part of a number of brain-computer interface (BCI) systems. The possible significance of the kind of imagery, involving rather kinesthetic or visual representations of actions, was addressed using the following experimental conditions: kinesthetic motor imagery (MIK), visual-motor imagery (MIV), motor execution (ME) and observation of movement (OOM). Based on multi-channel EEG recordings in 14 right-handed participants, we applied a learning classifier, the distinction sensitive learning vector quantization (DSLVQ) to identify relevant features (i.e., frequency bands, electrode sites) for recognition of the respective mental states. For ME and OOM, the overall classification accuracies were about 80%. The rates obtained for MIK (67%) were better than the results of MIV (56%). Moreover, the focus of activity during kinesthetic imagery was found close to the sensorimotor hand area, whereas visual-motor imagery did not reveal a clear spatial pattern. Consequently, to improve motor-imagery-based BCI control, user training should emphasize kinesthetic experiences instead of visual representations of actions.

EEG-based neuroprosthesis control: a step towards clinical practice.

This case study demonstrates the coupling of an electroencephalogram (EEG)-based Brain-Computer Interface (BCI) with an implanted neuroprosthesis (Freehand system). Because the patient was available for only 3 days, the goal was to demonstrate the possibility of a patient gaining control over the motor imagery-based Graz BCI system within a very short training period. By applying himself to an organized and coordinated training procedure, the patient was able to generate distinctive EEG-patterns by the imagination of movements of his paralyzed left hand. These patterns consisted of power decreases in specific frequency bands that could be classified by the BCI. The output signal of the BCI emulated the shoulder joystick usually used, and by consecutive imaginations the patient was able to switch between different grasp phases of the lateral grasp that the Freehand system provided. By performing a part of the grasp-release test, the patient was able to move a simple object from one place to another. The results presented in this work give evidence that Brain-Computer Interfaces are an option for the control of neuroprostheses in patients with high spinal cord lesions. The fact that the user learned to control the BCI in a comparatively short time indicates that this method may also be an alternative approach for clinical purposes.