Kim Dremstrup

Enhanced Low-Latency Detection of Motor Intention From EEG for Closed-Loop Brain-Computer Interface Applications

In recent years, the detection of voluntary motor intentions from electroencephalogram (EEG) has been used for triggering external devices in closed-loop brain-computer interface (BCI) research. Movement-related cortical potentials (MRCP), a type of slow cortical potentials, have been recently used for detection. In order to enhance the efficacy of closed-loop BCI systems based on MRCPs, a manifold method called Locality Preserving Projection, followed by a linear discriminant analysis (LDA) classifier (LPP-LDA) is proposed in this paper to detect MRCPs from scalp EEG in real time. In an online experiment on nine healthy subjects, LPP-LDA statistically outperformed the classic matched filter approach with greater true positive rate (79 ± 11% versus 68 ± 10%; p = 0.007) and less false positives (1.4 ± 0.8/min versus 2.3 ± 1.1/min; p = 0.016). Moreover, the proposed system performed detections with significantly shorter latency (315 ± 165 ms versus 460 ± 123 ms; p = 0.013), which is a fundamental characteristics to induce neuroplastic changes in closed-loop BCIs, following the Hebbian principle. In conclusion, the proposed system works as a generic brain switch, with high accuracy, low latency, and easy online implementation. It can thus be used as a fundamental element of BCI systems for neuromodulation and motor function rehabilitation.

Peripheral Electrical Stimulation Triggered by Self-Paced Detection of Motor Intention Enhances Motor Evoked Potentials

This paper proposes the development and experimental tests of a self-paced asynchronous brain-computer interfacing (BCI) system that detects movement related cortical potentials (MRCPs) produced during motor imagination of ankle dorsiflexion and triggers peripheral electrical stimulations timed with the occurrence of MRCPs to induce corticospinal plasticity. MRCPs were detected online from EEG signals in eight healthy subjects with a true positive rate (TPR) of 67.15±7.87% and false positive rate (FPR) of 22.05±9.07%. The excitability of the cortical projection to the target muscle (tibialis anterior) was assessed before and after the intervention through motor evoked potentials (MEP) using transcranial magnetic stimulation (TMS). The peak of the evoked potential significantly (P=0.02) increased after the BCI intervention by 53±43% (relative to preintervention measure), although the spinal excitability (tested by stretch reflexes) did not change. These results demonstrate for the first time that it is possible to alter the corticospinal projections to the tibialis anterior muscle by using an asynchronous BCI system based on online motor imagination that triggered peripheral stimulation. This type of repetitive proprioceptive feedback training based on self-generated brain signal decoding may be a requirement for purposeful skill acquisition in intact humans and in the rehabilitation of persons with brain damage.

Single-trial discrimination of type and speed of wrist movements from EEG recordings

OBJECTIVE The study explored the possibility of identifying movement type and speed from EEG recordings. METHODS EEG signals were acquired from 9 healthy volunteers during imagination of four tasks of the right wrist that involved two speeds (fast and slow) and two types of movement (wrist extension and rotation), each repeated 60 times in random order. Average movement-related cortical potentials (MRCPs) were compared among the four tasks. Moreover, single-trial classification was performed using the rebound rate of MRCP and the power in the mu and beta bands as features. RESULTS The rebound rate of the average MRCPs was greater for faster than for slower movements but did not depend on the type of movement. Accordingly, pairs of tasks executed at different speeds led to lower misclassification rate than pairs of tasks executed at the same speed. The average misclassification rate between task pairs was 21+/-2% for the best channel and task pair. CONCLUSION The task parameter speed can be discriminated in single-trial EEG traces with greater accuracy than the type of movement when tasks are executed at the same joint. SIGNIFICANCE The speed of movement execution may be included among the variables that characterize imagined tasks for brain-computer interface applications.

A Closed-Loop Brain–Computer Interface Triggering an Active Ankle–Foot Orthosis for Inducing Cortical Neural Plasticity

In this paper, we present a brain-computer interface (BCI) driven motorized ankle-foot orthosis (BCI-MAFO), intended for stroke rehabilitation, and we demonstrate its efficacy in inducing cortical neuroplasticity in healthy subjects with a short intervention procedure (~15 min). This system detects imaginary dorsiflexion movements within a short latency from scalp EEG through the analysis of movement-related cortical potentials (MRCPs). A manifold-based method, called locality preserving projection, detected the motor imagery online with a true positive rate of 73.0 ± 10.3%. Each detection triggered the MAFO to elicit a passive dorsiflexion. In nine healthy subjects, the size of the motorevoked potential (MEP) elicited by transcranial magnetic stimulation increased significantly immediately following and 30 min after the cessation of this BCI-MAFO intervention for ~15 min (p = 0.009 and p <; 0.001, respectively), indicating neural plasticity. In four subjects, the size of the short latency stretch reflex component did not change following the intervention, suggesting that the site of the induced plasticity was cortical. All but one subject also performed two control conditions where they either imagined only or where the MAFO was randomly triggered. Both of these control conditions resulted in no significant changes in MEP size (p = 0.38 and p = 0.15). The proposed system provides a fast and effective approach for inducing cortical plasticity through BCI and has potential in motor function rehabilitation following stroke.

A brain–computer interface for single-trial detection of gait initiation from movement related cortical potentials

OBJECTIVE Applications of brain-computer interfacing (BCI) in neurorehabilitation have received increasing attention. The intention to perform a motor task can be detected from scalp EEG and used to control rehabilitation devices, resulting in a patient-driven rehabilitation paradigm. In this study, we present and validate a BCI system for detection of gait initiation using movement related cortical potentials (MRCP). METHODS The templates of MRCP were extracted from 9-channel scalp EEG during gait initiation in 9 healthy subjects. Independent component analysis (ICA) was used to remove artifacts, and the Laplacian spatial filter was applied to enhance the signal-to-noise ratio of MRCP. Following these pre-processing steps, a matched filter was used to perform single-trial detection of gait initiation. RESULTS ICA preprocessing was shown to significantly improve the detection performance. With ICA preprocessing, across all subjects, the true positive rate (TPR) of the detection was 76.9±8.97%, and the false positive rate was 2.93±1.09 per minute. CONCLUSION The results demonstrate the feasibility of detecting the intention of gait initiation from EEG signals, on a single trial basis. SIGNIFICANCE The results are important for the development of new gait rehabilitation strategies, either for recovery/replacement of function or for neuromodulation.

Efficient neuroplasticity induction in chronic stroke patients by an associative brain-computer interface

Brain-computer interfaces (BCIs) have the potential to improve functionality in chronic stoke patients when applied over a large number of sessions. Here we evaluated the effect and the underlying mechanisms of three BCI training sessions in a double-blind sham-controlled design. The applied BCI is based on Hebbian principles of associativity that hypothesize that neural assemblies activated in a correlated manner will strengthen synaptic connections. Twenty-two chronic stroke patients were divided into two training groups. Movement-related cortical potentials (MRCPs) were detected by electroencephalography during repetitions of foot dorsiflexion. Detection triggered a single electrical stimulation of the common peroneal nerve timed so that the resulting afferent volley arrived at the peak negative phase of the MRCP (BCIassociative group) or randomly (BCInonassociative group). Fugl-Meyer motor assessment (FM), 10-m walking speed, foot and hand tapping frequency, diffusion tensor imaging (DTI) data, and the excitability of the corticospinal tract to the target muscle [tibialis anterior (TA)] were quantified. The TA motor evoked potential (MEP) increased significantly after the BCIassociative intervention, but not for the BCInonassociative group. FM scores (0.8 ± 0.46 point difference, P = 0.01), foot (but not finger) tapping frequency, and 10-m walking speed improved significantly for the BCIassociative group, indicating clinically relevant improvements. Corticospinal tract integrity on DTI did not correlate with clinical or physiological changes. For the BCI as applied here, the precise coupling between the brain command and the afferent signal was imperative for the behavioral, clinical, and neurophysiological changes reported. This association may become the driving principle for the design of BCI rehabilitation in the future. Indeed, no available BCIs can match this degree of functional improvement with such a short intervention.

Detection and classification of movement-related cortical potentials associated with task force and speed

OBJECTIVE In this study, the objective was to detect movement intentions and extract different levels of force and speed of the intended movement from scalp electroencephalography (EEG). We then estimated the performance of the closed loop system. APPROACH Cued movements were detected from continuous EEG recordings using a template of the initial phase of the movement-related cortical potential in 12 healthy subjects. The temporal features, extracted from the movement intention, were classified with an optimized support vector machine. The system performance was evaluated when combining detection with classification. MAIN RESULTS The system detected 81% of the movements and correctly classified 75 ± 9% and 80 ± 10% of these at the point of detection when varying the force and speed, respectively. When the detector was combined with the classifier, the system detected and correctly classified 64 ± 13% and 67 ± 13% of these movements. The system detected and incorrectly classified 21 ± 7% and 16 ± 9% of the movements. The movements were detected 317 ± 73 ms before the movement onset. SIGNIFICANCE The results indicate that it is possible to detect movement intentions with limited latencies, and extract and classify different levels of force and speed, which may be combined with assistive technologies for patient-driven neurorehabilitation.

Auditory and spatial navigation imagery in Brain–Computer Interface using optimized wavelets

Features extracted with optimized wavelets were compared with standard methods for a Brain-Computer Interface driven by non-motor imagery tasks. Two non-motor imagery tasks were used, Auditory Imagery of a familiar tune and Spatial Navigation Imagery through a familiar environment. The aims of this study were to evaluate which method extracts features that could be best differentiated and determine which channels are best suited for classification. EEG activity from 18 electrodes over the temporal and parietal lobes of nineteen healthy subjects was recorded. The features used were autoregressive and reflection coefficients extracted using autoregressive modeling with several model orders and marginals of the wavelet spaces generated by the Discrete Wavelet Transform (DWT). An optimization algorithm with 4 and 6 taps filters and mother wavelets from the Daubechies family were used. The classification was performed for each single channel and for all possible combination of two channels using a Bayesian Classifier. The best classification results were found using the marginals of the Optimized DWT spaces for filters with 6 taps in a 2 channels classification basis. Classification using 2 channels was found to be significantly better than using 1 channel (p<<0.01). The marginals of the optimized DWT using 6 taps filters showed to be significantly better than the marginals of the Daubechies family and autoregressive coefficients. The influence of the combination of number of channels and feature extraction method over the classification results was not significant (p=0.97).

Offline identification of imagined speed of wrist movements in paralyzed ALS patients from single-trial EEG

The study investigated the possibility of identifying the speed of an imagined movement from EEG recordings in amyotrophic lateral sclerosis (ALS) patients. EEG signals were acquired from four ALS patients during imagination of wrist extensions at two speeds (fast and slow), each repeated up to 100 times in random order. The movement-related cortical potentials (MRCPs) and averaged sensorimotor rhythm associated with the two tasks were obtained from the EEG recordings. Moreover, offline single-trial EEG classification was performed with discrete wavelet transform for feature extraction and support vector machine for classification. The speed of the task was encoded in the time delay of peak negativity in the MRCPs, which was shorter for faster than for slower movements. The average single-trial misclassification rate between speeds was 30.4 ± 3.5% when the best scalp location and time interval were selected for each individual. The scalp location and time interval leading to the lowest misclassification rate varied among patients. The results indicate that the imagination of movements at different speeds is a viable strategy for controlling a brain-computer interface system by ALS patients.

EMD-Based Temporal and Spectral Features for the Classification of EEG Signals Using Supervised Learning

This paper presents a novel method for feature extraction from electroencephalogram (EEG) signals using empirical mode decomposition (EMD). Its use is motivated by the fact that the EMD gives an effective time-frequency analysis of nonstationary signals. The intrinsic mode functions (IMF) obtained as a result of EMD give the decomposition of a signal according to its frequency components. We present the usage of upto third order temporal moments, and spectral features including spectral centroid, coefficient of variation and the spectral skew of the IMFs for feature extraction from EEG signals. These features are physiologically relevant given that the normal EEG signals have different temporal and spectral centroids, dispersions and symmetries when compared with the pathological EEG signals. The calculated features are fed into the standard support vector machine (SVM) for classification purposes. The performance of the proposed method is studied on a publicly available dataset which is designed to handle various classification problems including the identification of epilepsy patients and detection of seizures. Experiments show that good classification results are obtained using the proposed methodology for the classification of EEG signals. Our proposed method also compares favorably to other state-of-the-art feature extraction methods.