Epilepsy is a chronic brain disorder, and for at least one- third of epilepsy patients, medications do not adequately control seizures and surgery is the only potential cure. An automated seizure detector that requires a short period of normal EEG would shorten the seizure monitoring durations, decrease the need for manual assessment of large amount of recorded EEG data, and accordingly assist the neurologists focus on improving quality of care. In this work, we propose a novel approach based on the extended cumulative sum test to detect seizures using intracranial EEG. Different than the existing machine learning approaches, this method requires only a short period of normal EEG for training. In addition to a new proposed feature based on partial directed coherence and random graph theory, in this work, previously developed features used to characterize seizures are used as features in cumulative sum test for seizure detection. A total of 33 intracranial EEG recordings collected from a total of 9 patients corresponding to three different datasets have been used for the analysis purposes: (i) the first dataset includes 11 recorded EEG files (-12.5 min) from 4 patients; (ii) the second dataset includes 20 recorded EEG files (-30 min) from 4 patients; and (iii) two 24-hour long EEG files from a single patient. The proposed detector achieved a mean sensitivity and mean specificity for the first (0.77, 0.86), second (0.88, 0.9) and third datasets (0.92, 0.94) respectively. Statistical detection of seizures has shown success in detecting seizures without the need for highly customizable parameters or previously labelled EEG data. The proposed method could be used in real-time at hospital settings with a minimum requirement of training data.

In this paper, we introduce electroencephalography (EEG)- PDC based network connectivity average mean degrees (E-PDC) measure to analyze the interhemispheric interaction between the left and right motor cortices after stroke. E-PDC uses a graph and partial directed coherence (PDC) approach to quantify the directional functional connectivity between the motor cortices, which is not only altered after stroke but also is one of the important mechanisms linked with poor recovery of hand function. The brain activity between the two motor cortices is calculated via PDC and is used to form a graph. The PDC based network connectivity average mean degree of connectivity defined over this graph is defined as the E-PDC, which quantifies the directional connectivity between the two motor cortices. We preliminarily validated the novel E-PDC measure with three individuals with stroke, where one individual received a non-invasive brain stimulation (NIBS) intervention and the other two received sham-NIBS intervention. Unlike the two individuals who received sham-NIBS, the individual who received the NIBS intervention showed improvement in E-PDC after intervention, which strongly correlated with improvement in hand function after intervention (Fugl Meyer Upper Extremity Subscale and grip strength). This implies that the introduced E-PDC measure quantifies the interactions between the motor cortices and could be used to elucidate the underlying mechanism in restoring hand function after stroke.

Background: Functional transcranial Doppler (fTCD) is an ultrasound based neuroimaging technique used to assess neural activation that occurs during a cognitive task through measuring velocity of cerebral blood flow. New method: The objective of this paper is to investigate the feasibility of a 2-class and 3-class real-time BCI based on blood flow velocity in left and right middle cerebral arteries in response to mental rotation and word generation tasks. Statistical features based on a five-level wavelet decomposition were extracted from the fTCD signals. The Wilcoxon test and support vector machines (SVM), with a linear kernel, were employed for feature reduction and classification. Results: The experimental results showed that within approximately 3 s of the onset of the cognitive task average accuracies of 80.29%, and 82.35% were obtained for the mental rotation versus resting state and the word generation versus resting state respectively. The mental rotation task versus word generation task achieved an average accuracy of 79.72% within 2.24 s from the onset of the cognitive task. Furthermore, an average accuracy of 65.27% was obtained for the 3-class problem within 4.68 s. Comparison with existing methods: The results presented here provide significant improvement compared to the relevant fTCD-based systems presented in literature in terms of accuracy and speed. Specifically, the reported speed in this manuscript is at least 12 and 2.5 times faster than any existing binary and 3-class fTCD-based BCIs, respectively. Conclusions: These results show fTCD as a promising and viable candidate to be used towards developing a real-time BCI. Published by Elsevier B.V.

Although automated seizure detection methods using intracranial EEG (iEEG) have achieved high accuracy in previous studies, they acquire many labeled datasets. Also, due to the non-stationarity nature of seizures and the inter and intra-individual variability in signal characteristics, these methods are difficult to implement prospectively in clinical practice. We propose an automated seizure detection method using a cumulative sum (CUSUM) detector that can be used online with fewer training parameters and minimal overall training without the need for labeled datasets. The proposed seizure detector is composed of two main steps, feature extraction followed by detection.The features extracted are a line length (LL), relative energy (RE), coefficient of variation of amplitude (CVA), and the relative amplitude (RA).The main assumption for the extended CUSUM analysis is that the distributions corresponding to normal and seizure EEG are different. Feature vectors are calculated using windows of length N, subdivided into M segments of length n. At each point, the average of each of the M segments is calculated.Assuming that n is large enough, the central limit theorem applies and the sample mean vector of each segment follows a Gaussian distribution, which can be characterized by its mean and variance.A null hypothesis is formed that incoming data will be governed by the same distribution.During training, normal EEG data from the same subject is used to calculate the mean and variance bound distributions, representing the null hypothesis.During detection, for each incoming data segment, the log likelihood cumulative sum needs to be determined for each of these bound distributions.If the null hypothesis is rejected in any case, then a change is assumed to have occurred.Two 24-h long iEEG recordings containing 3 and 9 seizures respectively, were collected (sampling frequency of 2 kHz) from one patient, undergoing right parietal stereo-electroencephalography, (University of Pittsburgh IRB No. PRO15100311). Recordings were labeled by an expert closely familiar with the patients.For each iEEG file, the learning period was chosen to be the first seizure-free hour.The window length used for learning is 2.5 min. The CUSUM detector managed to detect the three labeled seizures of the first iEEG recording with a Good Detection Rate of 100%.While the Good Detection Rate results of the second iEEG recording are (LL = 78%, RE = 78%, RA = 88% and CVA = 78%). The number of false detections per hour results for the first EEG recording as follows (LL = 1.6, RE = 1.3, RA = 1.4 and CVA = 1.5). While for the second recording (LL = 1.3, RE = 1, RA = 1.2 and CVA = 1.25). Seizure detection using the extended CUSUM test appears to be a promising technique for clinical monitoring purposes.This novel method for automated seizure detection using iEEG is capable of differentiating seizures from normal activity, without the need for highly customizable parameters or previously labeled data.The method also could be applied toward scalp EEG data.

In this paper, the use of mutual information and the Learn++.NSE algorithm is proposed to create an EEG SSVEP BCI system that can select and utilize data sets originating from a group of users. In typical BCI systems, the nonstationarity in the EEG prevents the system from blindly applying training data from other users to the incoming data. Mutual information is introduced to select previous data sets that provide the most information about current random variables. A signed rank test was employed to show that this configuration outperformed both normal Learn++.NSE ensembles and LDA classifiers. This indicates that mutual information and ensemble learning techniques may prove useful in improving user transferability in SSVEP systems with low computational requirements.

Brain–Computer Interfaces (BCI) using Steady-State Visual Evoked Potentials (SSVEP) are sometimes used by injured patients seeking to use a computer. Canonical Correlation Analysis (CCA) is seen as state-of-the-art for SSVEP BCI systems. However, this assumes that the user has full control over their covert attention, which may not be the case. This introduces high calibration requirements when using other machine learning techniques. These may be circumvented by using transfer learning to utilize data from other participants. This paper proposes a combination of ensemble learning via Learn++ for Nonstationary Environments (Learn++.NSE)and similarity measures such as mutual information to identify ensembles of pre-existing data that result in higher classification. Results show that this approach performed worse than CCA in participants with typical SSVEP responses, but outperformed CCA in participants whose SSVEP responses violated CCA assumptions. This indicates that similarity measures and Learn++.NSE can introduce a transfer learning mechanism to bring SSVEP system accessibility to users unable to control their covert attention.

Brain-computer interfaces (BCIs) promise to promote a novel access channel for functional independence for individuals with severe speech and physical impairment (SSPI) that can occur as a result of numerous neurological diseases and injuries. Current BCI systems lack the robustness and accuracy to allow individuals with SSPI to complete tasks required for independent living (e.g. communication or navigation). We aim to develop a noninvasive hybrid BCI relying on two imaging modalities: Electroencephalography (EEG) and functional transcranial Doppler sonography (fTCD). Such hybrid BCI is expected to be sufficiently robust and accurate to be operated in a real-life environment.