A self-attention model for cross-subject seizure detection.

Epilepsy is a neurological disorder characterized by recurring seizures, detected by electroencephalography (EEG). EEG signals can be detected by manual time-consuming analysis and recently by automatic detection. The latter poses a significant challenge due to the high dimensional and non-stationary nature of EEG signals. Recently, deep learning (DL) techniques have emerged as valuable tools for seizure detection. In this study, a novel data-driven model based on DL, incorporating a self-attention mechanism (SAT), is proposed. One notable advantage of the proposed method is its simplicity in application, as the raw signal data is directly fed into the suggested network without requiring expertise in signal processing. The model leverages a one-dimensional convolutional neural network (CNN) to extract relevant features from EEG signals. These features are then passed through a long short-term memory (LSTM) module to benefit from its memory capabilities, along with a SAT mechanism. The key contribution of this paper lies in the addition of the SAT layer to the LSTM encoder, enabling enhanced exploration of the latent mapping during the encoding step. Cross-subject experiments revealed good performance of this approach with F1-score of 97.8% and 92.7% for binary and five-class epileptic seizure recognition tasks, respectively, on the public UCI dataset, and 97.9% on the CHB-MIT database, surpassing state-of-the-art DL performance. Besides, the proposed method exhibits robustness to inter-subject variability.

Is there a link between acetylcholinesterase, behaviour and density populations of the ragworm Hediste diversicolor?

The main objective of the present study was to explore the potential link between acetylcholinesterase (AChE) activity and burrowing behaviour of the ragworm Hediste diversicolor, which may have consequences at higher levels of biological organisation. Two complementary studies were conducted. AChE activity, at the sub-individual level, and behavioural responses, at the individual level, were evaluated in worms from the Loire estuary (France), whereas density and biomass of H. diversicolor were determined at the population level. A Spearman positive correlation between both biomarkers (AChE and burrowing) suggested that inhibition of AChE activity was linked to behaviour impairments. At the population level, lower AChE and behaviour activities were detected in worms corresponding to lower population density and biomass. These results provide direct empirical field evidence demonstrating the sensitivity of behaviour of H. diversicolor as a biomonitor of estuarine health status assessment.

Multichannel Time-Frequency Complexity Measures for the Analysis of Age-Related Changes in Neuromagnetic Resting-State Activity.

We propose new multichannel time-frequency complexity measures to evaluate differences on magnetoencephalograpy (MEG) recordings between healthy young and old subjects at rest at different spatial scales. After reviewing the Rényi and singular value decomposition entropies based on time-frequency representations, we introduce multichannel generalizations, using multilinear singular value decomposition for one of them. We test these quantities on synthetic data, illustrating how the introduced complexity measures focus on number of components, nonstationarity, and similarity across channels. Friedman tests are used to confirm the differences between young and old groups, and heterogeneity within groups. Experimental results show a consistent increase in complexity measures for the old group. When analyzing the topographical distribution of complexity values, we found clusters in the frontal sensors. The complexity measures here introduced seem to be a better indicator of the neurophysiologic changes of aging than power envelope connectivity. Here, we applied new multichannel time-frequency complexity measures to resting-state MEG recordings from healthy young and old subjects. We showed that these features are able to reveal regional clusters. The multichannel time-frequency complexities can be used to monitor the aging of subjects. They also allow a mutual information approach, and could be applied to a wider range of problems.

Investigating a transcriptomic approach on marine mussel hemocytes exposed to carbon nanofibers: An in vitro/in vivo comparison.

Manufactured nanomaterials are an ideal test case of the precautionary principle due to their novelty and potential environmental release. In the context of regulation, it is difficult to implement for manufactured nanomaterials as current testing paradigms identify risk late into the production process, slowing down innovation and increasing costs. One proposed concept, namely safe(r)-by-design, is to incorporate risk and hazard assessment into the design process of novel manufactured nanomaterials by identifying risks early. When investigating the manufacturing process for nanomaterials, differences between products will be very similar along key physicochemical properties and biological endpoints at the individual level may not be sensitive enough to detect differences whereas lower levels of biological organization may be able to detect these variations. In this sense, the present study used a transcriptomic approach on Mytilus edulis hemocytes following an in vitro and in vivo exposure to three carbon nanofibers created using different production methods. Integrative modeling was used to identify if gene expression could be in linked to physicochemical features. The results suggested that gene expression was more strongly associated with the carbon structure of the nanofibers than chemical purity. With respect to the in vitro/in vivo relationship, results suggested an inverse relationship in how the physicochemical impact gene expression.

A New Mutual Information Measure to Estimate Functional Connectivity: Preliminary Study.

Functional Connectivity (FC) is a powerful tool to investigate brain networks both in rest and while performing tasks. Functional magnetic resonance imaging (fMRI) gave good spatial estimation of FC but lacked the temporal resolution. Electroencephalography (EEG) allows estimating FC with good temporal resolution. In this study we introduce a new method based on Mutual Information and Multivariate Improved Weighted Multi-scale Permutation Entropy to estimate FC of brain using EEG. We applied this method on resting-state EEG signals from healthy children. Using network measures of nodes and Wilcoxon signed-rank test, we identified the most important nodes in the estimated networks. Comparing the localization of those outstanding nodes with the regions involved in resting-state networks (RSNs) estimated from fMRI showed that our proposal is efficient in the identification of nodes belonging to RSNs and could be used as a general estimator for FC without having to band-pass the signals into frequency bands.

Towards the development of a high throughput screening approach for Mytilus edulis hemocytes: A case study on silicon-based nanomaterials.

To have an understanding of potential mechanistic effects, sublethal endpoints able to discriminate between nanomaterials with similar physical and chemical features need to be used. In this sense, quantitative PCR was used to measure a battery of genes linked to a wide array of different cellular processes. Gene expression was measured in Mytilus edulis hemocytes following an in vitro and in vivo exposure to pure silicon (40 nm) and carbon-coated silicon (40 and 75 nm) after 24 h. Partial least squares discriminant analysis and correlation analysis were used to develop an integrative model, describing the relationship between genes, to identify which genes were important in describing responses to engineered nanomaterial exposure. The results suggested that some discriminations could be made based on the presence of a carbon coating or the alteration of size which could inform industrial patterns on ways to reduce the ecotoxicological impact of their product. The results also indicate that HTS on Mytilus hemocytes may be integrated into a safer-by-design approach but additional characterization of nanomaterial behavior in media is required to determine if it is a suitable alternative to in vivo testing.

Time-Varying Time-Frequency Complexity Measures for Epileptic EEG Data Analysis.

OBJECTIVE: Our goal is to use existing and to propose new time-frequency entropy measures that objectively evaluate the improvement on epileptic patients after medication by studying their resting state electroencephalography (EEG) recordings. An increase in the complexity of the signals would confirm an improvement in the general state of the patient. METHODS: We review the Rényi entropy based on time-frequency representations, along with its time-varying version. We also discuss the entropy based on singular value decomposition computed from a time-frequency representation, and introduce its corresponding time-dependant version. We test these quantities on synthetic data. Friedman tests are used to confirm the differences between signals (before and after proper medication). Principal component analysis is used for dimensional reduction prior to a simple threshold discrimination. RESULTS: Experimental results show a consistent increase in complexity measures in the different regions of the brain. These findings suggest that extracted features can be used to monitor treatment. When combined, they are useful for classification purposes, with areas under ROC curves higher than 0.93 in some regions. CONCLUSION: Here we applied time-frequency complexity measures to resting state EEG signals from epileptic patients for the first time. We also introduced a new time-varying complexity measure. We showed that these features are able to evaluate the treatment of the patient, and to perform classification. SIGNIFICANCE: The time-frequency complexities, and their time-varying versions, can be used to monitor the treatment of epileptic patients. They could be applied to a wider range of problems.

Automatic Detection and Classification of High-Frequency Oscillations in Depth-EEG Signals.

GOAL: Interictal high-frequency oscillations (HFOs [30-600 Hz]) have proven to be relevant biomarkers in epilepsy. In this paper, four categories of HFOs are considered: Gamma ([30-80 Hz]), high-gamma ([80-120 Hz]), ripples ([120-250 Hz]), and fast-ripples ([250-600 Hz]). A universal detector of the four types of HFOs is proposed. It has the advantages of 1) classifying HFOs, and thus, being robust to inter and intrasubject variability; 2) rejecting artefacts, thus being specific. METHODS: Gabor atoms are tuned to cover the physiological bands. Gabor transform is then used to detect HFOs in intracerebral electroencephalography (iEEG) signals recorded in patients candidate to epilepsy surgery. To extract relevant features, energy ratios, along with event duration, are investigated. Discriminant ratios are optimized so as to maximize among the four types of HFOs and artefacts. A multiclass support vector machine (SVM) is used to classify detected events. Pseudoreal signals are simulated to measure the performance of the method when the ground truth is known. RESULTS: Experiments are conducted on simulated and on human iEEG signals. The proposed method shows high performance in terms of sensitivity and false discovery rate. CONCLUSION: The methods have the advantages of detecting and discriminating all types of HFOs as well as avoiding false detections caused by artefacts. SIGNIFICANCE: Experimental results show the feasibility of a robust and universal detector.

Classification of high frequency oscillations in epileptic intracerebral EEG.

High Frequency Oscillations (HFOs 40-500 Hz), recorded from intracerebral electroencephalography (iEEG) in epileptic patients, are categorized into four distinct sub-bands (Gamma, High-Gamma, Ripples and Fast Ripples). They have recently been used as a reliable biomarker of epileptogenic zones. The objective of this paper is to investigate the possibility of discriminating between the different classes of HFOs which physiological/pathological value is critical for diagnostic but remains to be clarified. The proposed method is based on the definition of a relevant feature vector built from energy ratios (computed using Wavelet Transform-WT) in a-priori-defined frequency bands. It makes use of a multiclass Linear Discriminant Analysis (LDA) and is applied to iEEG signals recorded in patients candidate to epilepsy surgery. Results obtained from bootstrap on training/test datasets indicate high performances in terms of sensitivity and specificity.

A non-orthogonal SVD-based decomposition for phase invariant error-related potential estimation.

The estimation of the Error Related Potential from a set of trials is a challenging problem. Indeed, the Error Related Potential is of low amplitude compared to the ongoing electroencephalographic activity. In addition, simple summing over the different trials is prone to errors, since the waveform does not appear at an exact latency with respect to the trigger. In this work, we propose a method to cope with the discrepancy of these latencies of the Error Related Potential waveform and offer a framework in which the estimation of the Error Related Potential waveform reduces to a simple Singular Value Decomposition of an analytic waveform representation of the observed signal. The followed approach is promising, since we are able to explain a higher portion of the variance of the observed signal with fewer components in the expansion.

Gene-based multiclass cancer diagnosis with class-selective rejections.

Supervised learning of microarray data is receiving much attention in recent years. Multiclass cancer diagnosis, based on selected gene profiles, are used as adjunct of clinical diagnosis. However, supervised diagnosis may hinder patient care, add expense or confound a result. To avoid this misleading, a multiclass cancer diagnosis with class-selective rejection is proposed. It rejects some patients from one, some, or all classes in order to ensure a higher reliability while reducing time and expense costs. Moreover, this classifier takes into account asymmetric penalties dependent on each class and on each wrong or partially correct decision. It is based on nu-1-SVM coupled with its regularization path and minimizes a general loss function defined in the class-selective rejection scheme. The state of art multiclass algorithms can be considered as a particular case of the proposed algorithm where the number of decisions is given by the classes and the loss function is defined by the Bayesian risk. Two experiments are carried out in the Bayesian and the class selective rejection frameworks. Five genes selected datasets are used to assess the performance of the proposed method. Results are discussed and accuracies are compared with those computed by the Naive Bayes, Nearest Neighbor, Linear Perceptron, Multilayer Perceptron, and Support Vector Machines classifiers.