Search

Background: Transcranial magnetic stimulation combined with electroencephalography (TMS-EEG) is a powerful tool to probe human cortical excitability. The EEG response to TMS stimulation is altered by drugs active in the brain, with characteristic “fingerprints” obtained for drugs of known mechanisms of action. However, the extraction of specific features related to drug effects is not always straightforward as the complex TMS-EEG induced response profile is multi-dimensional, indexed over space, time, frequency, subjects and drug conditions. Analytical approaches can rely on a-priori assumptions within each dimension or on the implementation of cluster-based permutations which do not require preselection of specific limits but may be problematic when several experimental conditions are tested. Methods: We here propose an alternative data-driven approach based on PARAFAC tensor decomposition, which provides a parsimonious description of the main profiles underlying the multidimensional data. We validated reliability of PARAFAC on TMS-induced oscillations before extracting the features of two common anti-epileptic drugs (levetiracetam and lamotrigine) in an integrated manner. Results: PARAFAC revealed an effect of both drugs, significantly suppressing oscillations in the alpha range in the occipital region. Further, this effect was stronger under the intake of levetiracetam.Conclusions: This study demonstrates, for the first time, that PARAFAC can easily disentangle the effects of subject, drug condition, frequency, time and space in TMS-induced oscillations.

Topological metrics of graphs provide a natural way to describe the prominent features of various types of networks. Graph metrics describe the structure and interplay of graph edges and have found applications in many scientific fields. In this work, graph metrics are used in network estimation by developing optimisation methods that incorporate prior knowledge of a network's topology. The derivatives of graph metrics are used in gradient descent schemes for weighted undirected network denoising, network completion, and network decomposition. The successful performance of our methodology is shown in a number of toy examples and real-world datasets. Most notably, our work establishes a new link between graph theory, network science and optimisation., Comment: Accepted for publication in IEEE Transactions on Network Science and Engineering

The muscle synergy concept provides the best framework to understand motor control and it has been recently utilised in many applications such as prosthesis control. The current muscle synergy model relies on decomposing multi-channel surface Electromyography (EMG) signals into a synergy matrix (spatial mode) and its weighting function (temporal mode). This is done using several matrix factorisation techniques, with Non-negative matrix factorisation (NMF) being the most prominent method. Here, we introduce a 4th-order tensor muscle synergy model that extends the current state of the art by taking spectral information and repetitions (movements) into account. This adds more depth to the model and provides more synergistic information. In particular, we illustrate a proof-of-concept study where the Tucker3 tensor decomposition model was applied to a subset of wrist movements from the Ninapro database. The results showed the potential of Tucker3 tensor factorisation in finding patterns of muscle synergies with information about the movements and highlights the differences between the current and proposed model.

Wireless sensor networks enjoy many advantages over wired networks due to their ability to be deployed easily and flexibly in many scenarios. However, they suffer from the drawback that the environment may be unknown and hence the sensor network cannot easily be optimised for it. Furthermore, state-of-the-art studies only consider the detection and localisation performance separately. The main novelty of this work is that we compare the theoretical properties of three scanning strategies both in terms of their detection and localisation performance. We consider: a) sequential scanning, where all sensors scan the channels in sequence, b) groupwise scanning, where the sensors are split into groups with each one performing a sequential scan, and c) random scanning, where each sensor is assigned a channel at random. We demonstrate the theoretical properties of the strategies and perform a numerical evaluation for a typical radio surveillance scenario. The tradeoffs of the methods between detection and localisation performance are demonstrated to be dependent on the detection and localisation accuracy with respect to the number of sensors. Approximate knowledge of those curves can aid in the design of an optimal sensor scanning strategy.

Objective: The coupling between neuronal populations and its magnitude have been shown to be informative for various clinical applications. One method to estimate functional brain connectivity is with electroencephalography (EEG) from which the cross-spectrum between different sensor locations is derived. We wish to test the efficacy of tensor factorisation in the estimation of brain connectivity. Methods: An EEG model in the complex domain is derived that shows the suitability of the PARAFAC2 model. Complex tensor factorisation based on PARAFAC2 is used to decompose the EEG into scalp components described by the spatial, spectral, and complex trial profiles. A connectivity metric is also derived on the complex trial profiles of the extracted components. Results: Results on a benchmark EEG dataset confirmed that PARAFAC2 can estimate connectivity better than traditional tensor analysis such as PARAFAC within a range of signal-tonoise ratios. MVAR-ICA outperformed PARAFAC2 for very low signal-to-noise ratios while being inferior in most of the range, and in contrast to our method MVAR-ICA does not allow the estimation of trial to trial information. The analysis of EEG from patients with mild cognitive impairment or Alzheimer’s disease showed that PARAFAC2 identifies loss of brain connectivity agreeing with prior pathological knowledge. Conclusion: The complex PARAFAC2 algorithm is suitable for EEG connectivity estimation since it allows to extract meaningful coupled sources and provides better estimates than complex PARAFAC and MVAR-ICA. Significance: A new paradigm that employs complex tensor factorisation has demonstrated to be successful in identifying brain connectivity and the location of couples sources for both a benchmark and a real-world EEG dataset. This can enable future applications and has the potential to solve some the issues that deteriorate the performance of traditional connectivity metrics.

The muscle synergy concept provides a widely-accepted paradigm to break down the complexity of motor control. In order to identify the synergies, different matrix factorisation techniques have been used in a repertoire of fields such as prosthesis control and biomechanical and clinical studies. However, the relevance of these matrix factorisation techniques is still open for discussion since there is no ground truth for the underlying synergies. Here, we evaluate factorisation techniques and investigate the factors that affect the quality of estimated synergies. We compared commonly used matrix factorisation methods: Principal component analysis (PCA), Independent component analysis (ICA), Non-negative matrix factorization (NMF) and second-order blind identification (SOBI). Publicly available real data were used to assess the synergies extracted by each factorisation method in the classification of wrist movements. Synthetic datasets were utilised to explore the effect of muscle synergy sparsity, level of noise and number of channels on the extracted synergies. Results suggest that the sparse synergy model and a higher number of channels would result in better-estimated synergies. Without dimensionality reduction, SOBI showed better results than other factorisation methods. This suggests that SOBI would be an alternative when a limited number of electrodes is available but its performance was still poor in that case. Otherwise, NMF had the best performance when the number of channels was higher than the number of synergies. Therefore, NMF would be the best method for muscle synergy extraction., Keywords: Muscle synergy; Matrix factorisation; Surface electromyogram; Non-negative matrix factorisation; Second-order blind identification; Principal component analysis; Independent component analysis

Data is often plagued by noise which encumbers machine learning of clinically useful biomarkers and electroencephalogram (EEG) data is no exemption. Intracranial EEG (iEEG) data enhances the training of deep learning models of the human brain, yet is often prohibitive due to the invasive recording process. A more convenient alternative is to record brain activity using scalp electrodes. However, the inherent noise associated with scalp EEG data often impedes the learning process of neural models, achieving substandard performance. Here, an ensemble deep learning architecture for nonlinearly mapping scalp to iEEG data is proposed. The proposed architecture exploits the information from a limited number of joint scalp-intracranial recording to establish a novel methodology for detecting the epileptic discharges from the sEEG of a general population of subjects. Statistical tests and qualitative analysis have revealed that the generated pseudo-intracranial data are highly correlated with the true intracranial data. This facilitated the detection of IEDs from the scalp recordings where such waveforms are not often visible. As a real-world clinical application, these pseudo-iEEGs are then used by a convolutional neural network for the automated classification of intracranial epileptic discharges (IEDs) and non-IED of trials in the context of epilepsy analysis. Although the aim of this work was to circumvent the unavailability of iEEG and the limitations of sEEG, we have achieved a classification accuracy of 68% an increase of 6% over the previously proposed linear regression mapping.

Detection algorithms for electroencephalography (EEG) data, especially in the field of interictal epileptiform discharge (IED) detection, have traditionally employed handcrafted features, which utilized specific characteristics of neural responses. Although these algorithms achieve high accuracy, mere detection of an IED holds little clinical significance. In this paper, we consider deep learning for epileptic subjects to accommodate automatic feature generation from intracranial EEG data, while also providing clinical insight . Convolutional neural networks are trained in a subject independent fashion to demonstrate how meaningful features are automatically learned in a hierarchical process. We illustrate how the convolved filters in the deepest layers provide insight toward the different types of IEDs within the group, as confirmed by our expert clinicians. The morphology of the IEDs found in filters can help evaluate the treatment of a patient. To improve the learning of the deep model, moderately different score classes are utilized as opposed to binary IED and non-IED labels. The resulting model achieves state-of-the-art classification performance and is also invariant to time differences between the IEDs. This paper suggests that deep learning is suitable for automatic feature generation from intracranial EEG data, while also providing insight into the data.

Tensor factorisation is a decomposition method for high dimensional data that is used to estimate the prominent factors in some signal. Recently it has been employed with success in the biomedical fields. Regularised tensor factorisation attempts to alleviate overfitting and small sample size estimation errors by constraining the obtained solution to satisfy some metric. In this work, we provide a novel extension to the theory of graph regularisation for regularising multiple graphs and we employ graph regularised tensor factorisation on an electroencephalogram (EEG) dataset. We utilise brain connectivity networks as the basis of our graphs. Subsequently, we perform graph regularised tensor factorisation on the EEG data in order to reduce the noise and interference inherent to the EEG. Furthermore, we employ custom graphs that incorporate prior knowledge of our dataset. We demonstrate the efficacy of the algorithm theoretically and on some real EEG examples. Further applications of the algorithm can be neuroscience applications where there is prior knowledge of the relations between the data and in general in network science for datasets that can be expressed as tensors.

Detection algorithms for electroencephalography (EEG) data typically employ handcrafted features that take advantage of the signal's specific properties. In the field of interictal epileptic discharge (IED) detection, the feature representation that provides optimal classification performance is still an unresolved issue. In this paper, we consider deep learning for automatic feature generation from epileptic intracranial EEG data in the time domain. Specifically, we consider convolutional neural networks (CNNs) in a subject independent fashion and demonstrate that meaningful features, representing IEDs are automatically learned. The resulting model achieves state of the art classification performance, provides insights for the different types of IEDs within the group, and is invariant to time differences between the IEDs. This study suggests that automatic feature generation via deep learning is suitable for IEDs and EEG in general.

Objective Constant changes in developing children's brains can pose a challenge in EEG dependant technologies. Advancing signal processing methods to identify developmental differences in paediatric populations could help improve function and usability of such technologies. Taking advantage of the multi-dimensional structure of EEG data through tensor analysis may offer a framework for extracting relevant developmental features of paediatric datasets. A proof of concept is demonstrated through identifying latent developmental features in resting-state EEG. Approach Three paediatric datasets ([Formula: see text]) were analyzed using a two-step constrained parallel factor (PARAFAC) tensor decomposition. Subject age was used as a proxy measure of development. Classification used support vector machines (SVM) to test if PARAFAC identified features could predict subject age. The results were cross-validated within each dataset. Classification analysis was complemented by visualization of the high-dimensional feature structures using t-distributed stochastic neighbour embedding (t-SNE) maps. Main results Development-related features were successfully identified for the developmental conditions of each dataset. SVM classification showed the identified features could accurately predict subject at a significant level above chance for both healthy and impaired populations. t-SNE maps revealed suitable tensor factorization was key in extracting the developmental features. Significance The described methods are a promising tool for identifying latent developmental features occurring throughout childhood EEG.

A novel algorithm for the localization of event-related potential (ERP) sources within the brain is proposed here. In this technique, spatial notch filters are developed to exploit the multichannel electroencephalogram data together with a model of ERP with variable parameters in order to accurately localize the corresponding ERP signal sources. The algorithm is robust in the presence of reasonably high noise. The performance of the proposed system has been compared to that of linear constrained minimum variance (LCMV) beamformer for different noise and correlation levels and its superiority has been demonstrated.

Item does not contain fulltext Brain-Computer Interface (BCI) systems are traditionally designed by taking into account user-specific data to enable practical use. More recently, subject independent (SI) classification algorithms have been developed which bypass the subject specific adaptation and enable rapid use of the system. A brain switch is a particular BCI system where the system is required to distinguish from two separate mental tasks corresponding to the on-off commands of a switch. Such applications require a low false positive rate (FPR) while having an acceptable response time (RT) until the switch is activated. In this work, we develop a methodology that produces optimal brain switch behavior through subject specific (SS) adaptation of: a) a multitrial prediction combination model and b) an SI classification model. We propose a statistical model of combining classifier predictions that enables optimal FPR calibration through a short calibration session. We trained an SI classifier on a training synchronous dataset and tested our method on separate holdout synchronous and asynchronous brain switch experiments. Although our SI model obtained similar performance between training and holdout datasets, 86% and 85% for the synchronous and 69% and 66% for the asynchronous the between subject FPR and TPR variability was high (up to 62%). The short calibration session was then employed to alleviate that problem and provide decision thresholds that achieve when possible a target FPR=1% with good accuracy for both datasets. 10 p.

Contains fulltext : 157484.pdf (Publisher’s version ) (Open Access) Objective. Patients undergoing general anesthesia may awaken and become aware of the surgical procedure. Due to neuromuscular blocking agents, patients could be conscious yet unable to move. Using brain–computer interface (BCI) technology, it may be possible to detect movement attempts from the EEG. However, it is unknown how an anesthetic influences the brain response to motor tasks. Approach. We tested the offline classification performance of a movement-based BCI in 12 healthy subjects at two effect-site concentrations of propofol. For each subject a second classifier was trained on the subject’s data obtained before sedation, then tested on the data obtained during sedation (‘transfer classification’). Main results. At concentration 0.5 μ g ml -1 , despite an overall propofol EEG effect, the mean single trial classification accuracy was 85% (95% CI 81%- 89%), and 83% (79%-88%) for the transfer classification. At 1.0 μ g ml -1 , the accuracies were 81% (76%-86%), and 72% (66%-79%), respectively. At the highest propofol concentration for four subjects, unlike the remaining subjects, the movement-related brain response had been largely diminished, and the transfer classification accuracy was not significantly above chance. These subjects showed a slower and more erratic task response, indicating an altered state of consciousness distinct from that of the other subjects. Significance. The results show the potential of using a BCI to detect intra-operative awareness and justify further development of this paradigm. At the same time, the relationship between motor responses and consciousness and its clinical relevance for intraoperative awareness requires further investigation. 9 p.

Contains fulltext : 154964.pdf (Publisher’s version ) (Open Access) Brain-Computer Interfaces (BCIs) have the potential to detect intraoperative awareness during general anaesthesia. Traditionally, BCI research is aimed at establishing or improving communication and control for patients with permanent paralysis. Patients experiencing intraoperative awareness also lack the means to communicate after administration of a neuromuscular blocker, but may attempt to move. This study evaluates the principle of detecting attempted movements from the electroencephalogram (EEG) during local temporary neuromuscular blockade. EEG was obtained from four healthy volunteers making 3-second hand movements, both before and after local administration of rocuronium in one isolated forearm. Using offline classification analysis we investigated whether the attempted movements the participants made during paralysis could be distinguished from the periods when they did not move or attempt to move. Attempted movement trials were correctly identified in 81 (68-94)% (mean (95% CI)) and 84 (74-93)% of the cases using 30 and 9 EEG channels, respectively. Similar accuracies were obtained when training the classifier on the participants' actual movements. These results provide proof of the principle that a BCI can detect movement attempts during neuromuscular blockade. Based on this, in the future a BCI may serve as a communication channel between a patient under general anaesthesia and the anaesthesiologist. 11 p.

Item does not contain fulltext Combining electrophysiological and hemodynamic features is a novel approach for improving current performance of brain switches based on sensorimotor rhythms (SMR). This study was conducted with a dual purpose: to test the feasibility of using a combined electroencephalogram/functional near-infrared spectroscopy (EEG-fNIRS) SMR-based brain switch in patients with tetraplegia, and to examine the performance difference between motor imagery and motor attempt for this user group. A general improvement was found when using both EEG and fNIRS features for classification as compared to using the single-modality EEG classifier, with average classification rates of 79% for attempted movement and 70% for imagined movement. For the control group, rates of 87% and 79% were obtained, respectively, where the "attempted movement" condition was replaced with "actual movement." A combined EEG-fNIRS system might be especially beneficial for users who lack sufficient control of current EEG-based brain switches. The average classification performance in the patient group for attempted movement was significantly higher than for imagined movement using the EEG-only as well as the combined classifier, arguing for the case of a paradigm shift in current brain switch research. 8 p.

Two series of Electroencephalogram (EEG) measurements indicated that average auditory event-related potentials (ERPs) elicited by the disyllabic sound /asu/ were different between Japanese and English native listeners. Significant differences were observed in the time window where the P1-N1-P2 complex for /a/ is expected. This difference may be due to the absence/presence of the Auditory Change Complex (ACC) elicited by /s/. Furthermore, by combining the P1-N1-P2 complex elicited by each component of /asu/ (/a//s//u/) recorded individually, it was possible to compose ERPs similar to those elicited by /asu/. Interestingly, the optimized weights of /s/ were significantly lower for Japanese than for native- English listeners, suggesting that the trace of the ACC associated with /s/ was less visible in the actual ERP response to /asu/ for Japanese native listeners. These results may together suggest that Japanese and English native individuals process the /s/ in /asu/ differently and that the ACC is sensitive to language-specific perceptual categories.

Interictal epileptiform discharges (IEDs) are transient neural electrical activities that occur in the brain of patients with epilepsy. A problem with the inspection of IEDs from the scalp electroencephalogram (sEEG) is that for a subset of epileptic patients, there are no visually discernible IEDs on the scalp, rendering the above procedures ineffective, both for detection purposes and algorithm evaluation. On the other hand, intracranially placed electrodes yield a much higher incidence of visible IEDs as compared to concurrent scalp electrodes. In this work, we utilize concurrent scalp and intracranial EEG (iEEG) from a group of temporal lobe epilepsy (TLE) patients with low number of scalp-visible IEDs. The aim is to determine whether by considering the timing information of the IEDs from iEEG, the resulting concurrent sEEG contains enough information for the IEDs to be reliably distinguished from non-IED segments. We develop an automatic detection algorithm which is tested in a leave-subject-out fashion, where each test subject’s detection algorithm is based on the other patients’ data. The algorithm obtained a [Formula: see text] accuracy in recognizing scalp IED from non-IED segments with [Formula: see text] accuracy when trained and tested on the same subject. Also, it was able to identify nonscalp-visible IED events for most patients with a low number of false positive detections. Our results represent a proof of concept that IED information for TLE patients is contained in scalp EEG even if they are not visually identifiable and also that between subject differences in the IED topology and shape are small enough such that a generic algorithm can be used.

Estimating the P300 subcomponents of event related potentials (ERPs) is very important in the fields of psychiatry and neurology. The characteristics of these brain signals, such as latency, location, strength, and variation, can give useful insights of the person's condition. In particular, the signals' characteristics can aid in the diagnosis and monitoring of some specific psychiatric diseases such as schizophrenia of various stages, and can be a useful factor for their treatment. In this paper we employ a new filtering algorithm, incorporating prior knowledge of the shape of such components. Then we employ a novel localization algorithm to track the location of the P300 components trial by trial.

Separation and localisation of P300 sources and their constituent subcomponents for both visual and audio stimulations is investigated in this paper. An effective constrained blind source separation (CBSS) algorithm is developed for this purpose. The algorithm is an extension of the Infomax BSS system for which a measure of distance between a carefully measured P300 and the estimated sources is used as a constraint. During separation, the proposed CBSS method attempts to extract the corresponding P300 signals. The locations of the corresponding sources are then estimated with some indeterminancy in the results. It can be seen that the locations of the sources change for a schizophrenic patient. The experimental results verify the statistical significance of the method and its potential application in the diagnosis and monitoring of schizophrenia.

To separate and localize the P300 sources within the brain, a robust constrained blind source separation (CBSS) algorithm has been proposed. The algorithm is an extension of the Infomax algorithm, based on minimization of mutual information, for which a reference P300 signal is used as a constraint. The reference signal forces the unmixing matrix to separate the sources of both auditory and visual P300 resulting from the corresponding stimulations. The constrained problem is then converted to an unconstrained problem by means of a set of nonlinear penalty functions. The P300 sources are then localized based on electrode source inner products.