Complex Tensor Factorization With PARAFAC2 for the Estimation of Brain Connectivity From the EEG.

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 factorization in the estimation of brain connectivity. An EEG model in the complex domain is derived that shows the suitability of the PARAFAC2 model. Complex tensor factorization 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 on a benchmark EEG dataset confirmed that the PARAFAC2 can estimate connectivity better than traditional tensor analysis such as PARAFAC within a range of signal-to-noise 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 the EEG from patients with mild cognitive impairment or Alzheimer's disease showed that the PARAFAC2 identifies loss of brain connectivity agreeing with prior pathological knowledge. The complex PARAFAC2 algorithm is suitable for the EEG connectivity estimation since it allows to extract meaningful-coupled sources and provides better estimates than complex PARAFAC and MVAR-ICA. A new paradigm that employs complex tensor factorization 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.

Evaluation of matrix factorisation approaches for muscle synergy extraction.

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.

Deep Neural Architectures for Mapping Scalp to Intracranial EEG.

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.

On the use of higher-order tensors to model muscle synergies.

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.

Detection of Interictal Discharges With Convolutional Neural Networks Using Discrete Ordered Multichannel Intracranial EEG.

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.

Optimal Multitrial Prediction Combination and Subject-Specific Adaptation for Minimal Training Brain Switch Designs.

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.

Detection of Intracranial Signatures of Interictal Epileptiform Discharges from Concurrent Scalp EEG.

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.

Decoding motor responses from the EEG during altered states of consciousness induced by propofol.

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 µg 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 µg 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.

Detection of attempted movement from the EEG during neuromuscular block: proof of principle study in awake volunteers.

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.

Combined EEG-fNIRS decoding of motor attempt and imagery for brain switch control: an offline study in patients with tetraplegia.

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.

Decoding of single-trial auditory mismatch responses for online perceptual monitoring and neurofeedback.

Multivariate pattern classification methods are increasingly applied to neuroimaging data in the context of both fundamental research and in brain-computer interfacing approaches. Such methods provide a framework for interpreting measurements made at the single-trial level with respect to a set of two or more distinct mental states. Here, we define an approach in which the output of a binary classifier trained on data from an auditory mismatch paradigm can be used for online tracking of perception and as a neurofeedback signal. The auditory mismatch paradigm is known to induce distinct perceptual states related to the presentation of high- and low-probability stimuli, which are reflected in event-related potential (ERP) components such as the mismatch negativity (MMN). The first part of this paper illustrates how pattern classification methods can be applied to data collected in an MMN paradigm, including discussion of the optimization of preprocessing steps, the interpretation of features and how the performance of these methods generalizes across individual participants and measurement sessions. We then go on to show that the output of these decoding methods can be used in online settings as a continuous index of single-trial brain activation underlying perceptual discrimination. We conclude by discussing several potential domains of application, including neurofeedback, cognitive monitoring and passive brain-computer interfaces.

Source localization of event-related potentials incorporating spatial notch filters.

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.