Delve into Multiple Sclerosis (MS) lesion exploration: A modified attention U-Net for MS lesion segmentation in Brain MRI.

Multiple Sclerosis (MS) is a Central Nervous System (CNS) disease that Magnetic Resonance Imaging (MRI) system can detect and segment its lesions. Artificial Neural Networks (ANNs) recently reached a noticeable performance in finding MS lesions from MRI. U-Net and Attention U-Net are two of the most successful ANNs in the field of MS lesion segmentation. In this work, we proposed a framework to segment MS lesions in Fluid-Attenuated Inversion Recovery (FLAIR) and T2 MRI images by modified U-Net and modified Attention U-Net. For this purpose, we developed some extra preprocessing on MRI scans, made modifications in the loss function of U-Net and Attention U-Net, and proposed using the union of FLAIR and T2 predictions to reach a better performance. Results show that the union of FLAIR and T2 predicted masks by the modified Attention U-Net reaches the performance of 82.30% in terms of Dice Similarity Coefficient (DSC) in the test dataset, which is a considerable improvement compared to the previous works.

Dimensionality Transcending: A Method for Merging BCI Datasets With Different Dimensionalities.

OBJECTIVE: We present a transfer learning method for datasets with different dimensionalities, coming from different experimental setups but representing the same physical phenomena. We focus on the case where the data points are symmetric positive definite (SPD) matrices describing the statistical behavior of EEG-based brain computer interfaces (BCI). METHOD: Our proposal uses a two-step procedure that transforms the data points so that they become matched in terms of dimensionality and statistical distribution. In the dimensionality matching step, we use isometric transformations to map each dataset into a common space without changing their geometric structures. The statistical matching is done using a domain adaptation technique adapted for the intrinsic geometry of the space where the datasets are defined. RESULTS: We illustrate our proposal on time series obtained from BCI systems with different experimental setups (e.g., different number of electrodes, different placement of electrodes). The results show that the proposed method can be used to transfer discriminative information between BCI recordings that, in principle, would be incompatible. CONCLUSION AND SIGNIFICANCE: Such findings pave the way to a new generation of BCI systems capable of reusing information and learning from several sources of data despite differences in their electrodes positioning.

Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry.

Hyperspectral image unmixing has proven to be a useful technique to interpret hyperspectral data, and is a prolific research topic in the community. Most of the approaches used to perform linear unmixing are based on convex geometry concepts, because of the strong geometrical structure of the linear mixing model. However, many algorithms based on convex geometry are still used in spite of the underlying model not considering the intra-class variability of the materials. A natural question is to wonder to what extent these concepts and tools (Intrinsic Dimensionality estimation, endmember extraction algorithms, pixel purity) are still relevant when spectral variability comes into play. In this paper, we first analyze their robustness in a case where the linear mixing model holds in each pixel, but the endmembers vary in each pixel according to a prescribed variability model. In the light of this analysis, we propose an integrated unmixing chain which tries to adress the shortcomings of the classical tools used in the linear case, based on our previously proposed extended linear mixing model. We show the interest of the proposed approach on simulated and real datasets.

Temporally Nonstationary Component Analysis; Application to Noninvasive Fetal Electrocardiogram Extraction.

OBJECTIVE: Mixtures of temporally nonstationary signals are very common in biomedical applications. The nonstationarity of the source signals can be used as a discriminative property for signal separation. Herein, a semi-blind source separation algorithm is proposed for the extraction of temporally nonstationary components from linear multichannel mixtures of signals and noises. METHODS: A hypothesis test is proposed for the detection and fusion of temporally nonstationary events, by using ad hoc indexes for monitoring the first and second order statistics of the innovation process. As proof of concept, the general framework is customized and tested over noninvasive fetal cardiac recordings acquired from the maternal abdomen, over publicly available datasets, using two types of nonstationarity detectors: 1) a local power variations detector, and 2) a model-deviations detector using the innovation process properties of an extended Kalman filter. RESULTS: The performance of the proposed method is assessed in presence of white and colored noise, in different signal-to-noise ratios. CONCLUSION AND SIGNIFICANCE: The proposed scheme is general and it can be used for the extraction of nonstationary events and sample deviations from a presumed model in multivariate data, which is a recurrent problem in many machine learning applications.

Hyperspectral Image Unmixing With Endmember Bundles and Group Sparsity Inducing Mixed Norms.

Hyperspectral images provide much more information than conventional imaging techniques, allowing a precise identification of the materials in the observed scene, but because of the limited spatial resolution, the observations are usually mixtures of the contributions of several materials. The spectral unmixing problem aims at recovering the spectra of the pure materials of the scene (endmembers), along with their proportions (abundances) in each pixel. In order to deal with the intra-class variability of the materials and the induced spectral variability of the endmembers, several spectra per material, constituting endmember bundles, can be considered. However, the usual abundance estimation techniques do not take advantage of the particular structure of these bundles, organized into groups of spectra. In this paper, we propose to use group sparsity by introducing mixed norms in the abundance estimation optimization problem. In particular, we propose a new penalty, which simultaneously enforces group and within-group sparsity, to the cost of being nonconvex. All the proposed penalties are compatible with the abundance sum-to-one constraint, which is not the case with traditional sparse regression. We show on simulated and real datasets that well-chosen penalties can significantly improve the unmixing performance compared to classical sparse regression techniques or to the naive bundle approach.

Riemannian Procrustes Analysis: Transfer Learning for Brain-Computer Interfaces.

OBJECTIVE: This paper presents a Transfer Learning approach for dealing with the statistical variability of electroencephalographic (EEG) signals recorded on different sessions and/or from different subjects. This is a common problem faced by brain-computer interfaces (BCI) and poses a challenge for systems that try to reuse data from previous recordings to avoid a calibration phase for new users or new sessions for the same user. METHOD: We propose a method based on Procrustes analysis for matching the statistical distributions of two datasets using simple geometrical transformations (translation, scaling, and rotation) over the data points. We use symmetric positive definite matrices (SPD) as statistical features for describing the EEG signals, so the geometrical operations on the data points respect the intrinsic geometry of the SPD manifold. Because of its geometry-aware nature, we call our method the Riemannian Procrustes analysis (RPA). We assess the improvement in transfer learning via RPA by performing classification tasks on simulated data and on eight publicly available BCI datasets covering three experimental paradigms (243 subjects in total). RESULTS: Our results show that the classification accuracy with RPA is superior in comparison to other geometry-aware methods proposed in the literature. We also observe improvements in ensemble classification strategies when the statistics of the datasets are matched via RPA. CONCLUSION AND SIGNIFICANCE: We present a simple yet powerful method for matching the statistical distributions of two datasets, thus paving the way to BCI systems capable of reusing data from previous sessions and avoid the need of a calibration procedure.

Supervised Bayesian Source Separation of Nonlinear Mixtures for Quantitative Analysis of Gas Mixtures.

In medical applications, quantitative analysis of breath may open new prospects for diagnosis or for patient monitoring. To detect acetone, a breath biomarker for diabetes, we use a single metal-oxide (MOX) gas sensor working in a dual temperature mode. We propose a linear-quadratic model to describe the mixing model mapping gas concentrations to MOX sensor responses. In this purpose, it is necessary to inverse the nonlinear problem in order to quantify the component of the gas mixture. As a proof of concept, we study a mixture of two gases, acetone and ethanol diluted in air buffer. In order to estimate the concentration of each gas, we introduce a supervised Bayesian source separation method. Based on MCMC stochastic sampling methods to estimate the mean of the posterior distribution, this Bayesian approach is robust to noise for solving this ill-posed non-linear inversion problem. We analyze the performance on a set of samples associated with a set of gas concentration covering the range suitable for exhaled breath. We use a cross-validation approach, calibrating the mixing parameters with some samples and validating the source estimation with others. Our new supervised method applied on a linear-quadratic model allows to estimate acetone and ethanol concentration with a precision of around 2 ppm.

A Linear-Quadratic Model for the Quantification of a Mixture of Two Diluted Gases with a Single Metal Oxide Sensor.

The aim of our work is to quantify two gases (acetone and ethanol) diluted in an air buffer using only a single metal oxide (MOX) sensor. We took advantage of the low selectivity of the MOX sensor, exploiting a dual-temperature mode. Working at two temperatures of the MOX sensitive layer allowed us to obtain diversity in the measures. Two virtual sensors were created to characterize our gas mixture. We presented a linear-quadratic mixture sensing model which was closer to the experimental data. To validate this model and the experimental protocol, we inverted the system of quadratic equations to quantify a mixture of the two gases. The linear-quadratic model was compared to the bilinear model proposed in the literature. We presented an experimental evaluation on mixtures made of a few ppm of acetone and ethanol, and we obtained a precision close to the ppm. This is an important step towards medical applications, particularly in terms of diabetes, to deliver a non-invasive measure with a low-cost device.

ECG fiducial point extraction using switching Kalman filter.

In this paper, we propose a novel method for extracting fiducial points (FPs) of the beats in electrocardiogram (ECG) signals using switching Kalman filter (SKF). In this method, according to McSharry's model, ECG waveforms (P-wave, QRS complex and T-wave) are modeled with Gaussian functions and ECG baselines are modeled with first order auto regressive models. In the proposed method, a discrete state variable called "switch" is considered that affects only the observation equations. We denote a mode as a specific observation equation and switch changes between 7 modes and corresponds to different segments of an ECG beat. At each time instant, the probability of each mode is calculated and compared among two consecutive modes and a path is estimated, which shows the relation of each part of the ECG signal to the mode with the maximum probability. ECG FPs are found from the estimated path. For performance evaluation, the Physionet QT database is used and the proposed method is compared with methods based on wavelet transform, partially collapsed Gibbs sampler (PCGS) and extended Kalman filter. For our proposed method, the mean error and the root mean square error across all FPs are 2 ms (i.e. less than one sample) and 14 ms, respectively. These errors are significantly smaller than those obtained using other methods. The proposed method achieves lesser RMSE and smaller variability with respect to others.

Transfer Learning: A Riemannian Geometry Framework With Applications to Brain-Computer Interfaces.

OBJECTIVE: This paper tackles the problem of transfer learning in the context of electroencephalogram (EEG)-based brain-computer interface (BCI) classification. In particular, the problems of cross-session and cross-subject classification are considered. These problems concern the ability to use data from previous sessions or from a database of past users to calibrate and initialize the classifier, allowing a calibration-less BCI mode of operation. METHODS: Data are represented using spatial covariance matrices of the EEG signals, exploiting the recent successful techniques based on the Riemannian geometry of the manifold of symmetric positive definite (SPD) matrices. Cross-session and cross-subject classification can be difficult, due to the many changes intervening between sessions and between subjects, including physiological, environmental, as well as instrumental changes. Here, we propose to affine transform the covariance matrices of every session/subject in order to center them with respect to a reference covariance matrix, making data from different sessions/subjects comparable. Then, classification is performed both using a standard minimum distance to mean classifier, and through a probabilistic classifier recently developed in the literature, based on a density function (mixture of Riemannian Gaussian distributions) defined on the SPD manifold. RESULTS: The improvements in terms of classification performances achieved by introducing the affine transformation are documented with the analysis of two BCI datasets. CONCLUSION AND SIGNIFICANCE: Hence, we make, through the affine transformation proposed, data from different sessions and subject comparable, providing a significant improvement in the BCI transfer learning problem.

ECG segmentation and fiducial point extraction using multi hidden Markov model.

In this paper, we propose a novel method for extracting fiducial points (FPs) of electrocardiogram (ECG) signals. We propose the use of multi hidden Markov model (MultiHMM) as opposed to the traditional use of Classic HMM. In the MultiHMM method, each segment of an ECG beat is represented by a separate ergodic continuous density HMM. Each HMM has different state number and is trained separately. In the test step, the log-likelihood of two consecutive HMMs is compared and a path is estimated, which shows the correspondence of each part of the ECG signal to the HMM with the maximum log-likelihood. Fiducial points are estimated from the obtained path. For performance evaluation, the Physionet QT database and a Swine ECG database are used and the proposed method is compared with the Classic HMM and a method based on partially collapsed Gibbs sampler (PCGS). In our evaluation using the QT database, we also compare the results with low-pass differentiation, hybrid feature extraction algorithm, a method based on the wavelet transform and three HMM-based approaches. For the Swine database, the root mean square error (RMSE) values, across all FPs for MultiHMM, Classic HMM and PCGS methods are 13, 21 and 40ms, respectively and the MultiHMM exhibits smaller error variability than other methods. For the QT database, RMSE values for MultiHMM, Classic HMM, Wavelet and PCGS methods are 10, 17, 26 and 38ms, respectively. Our results demonstrate that our proposed MultiHMM approach outperforms other benchmark methods that exist in the literature; therefore can be used in practical ECG fiducial point extraction.

Blind Hyperspectral Unmixing Using an Extended Linear Mixing Model to Address Spectral Variability.

Spectral unmixing is one of the main research topics in hyperspectral imaging. It can be formulated as a source separation problem, whose goal is to recover the spectral signatures of the materials present in the observed scene (called endmembers) as well as their relative proportions (called fractional abundances), and this for every pixel in the image. A linear mixture model (LMM) is often used for its simplicity and ease of use, but it implicitly assumes that a single spectrum can be completely representative of a material. However, in many scenarios, this assumption does not hold, since many factors, such as illumination conditions and intrinsic variability of the endmembers, induce modifications on the spectral signatures of the materials. In this paper, we propose an algorithm to unmix hyperspectral data using a recently proposed extended LMM. The proposed approach allows a pixelwise spatially coherent local variation of the endmembers, leading to scaled versions of reference endmembers. We also show that the classic nonnegative least squares, as well as other approaches to tackle spectral variability can be interpreted in the framework of this model. The results of the proposed algorithm on two different synthetic datasets, including one simulating the effect of topography on the measured reflectance through physical modelling, and on two real data sets, show that the proposed technique outperforms other methods aimed at addressing spectral variability, and can provide an accurate estimation of endmember variability along the scene because of the scaling factors estimation.

Dynamical Spectral Unmixing of Multitemporal Hyperspectral Images.

In this paper, we consider the problem of unmixing a time series of hyperspectral images. We propose a dynamical model based on linear mixing processes at each time instant. The spectral signatures and fractional abundances of the pure materials in the scene are seen as latent variables, and assumed to follow a general dynamical structure. Based on a simplified version of this model, we derive an efficient spectral unmixing algorithm to estimate the latent variables by performing alternating minimizations. The performance of the proposed approach is demonstrated on synthetic and real multitemporal hyperspectral images.

ECG denoising and fiducial point extraction using an extended Kalman filtering framework with linear and nonlinear phase observations.

In this paper we propose an efficient method for denoising and extracting fiducial point (FP) of ECG signals. The method is based on a nonlinear dynamic model which uses Gaussian functions to model ECG waveforms. For estimating the model parameters, we use an extended Kalman filter (EKF). In this framework called EKF25, all the parameters of Gaussian functions as well as the ECG waveforms (P-wave, QRS complex and T-wave) in the ECG dynamical model, are considered as state variables. In this paper, the dynamic time warping method is used to estimate the nonlinear ECG phase observation. We compare this new approach with linear phase observation models. Using linear and nonlinear EKF25 for ECG denoising and nonlinear EKF25 for fiducial point extraction and ECG interval analysis are the main contributions of this paper. Performance comparison with other EKF-based techniques shows that the proposed method results in higher output SNR with an average SNR improvement of 12 dB for an input SNR of -8 dB. To evaluate the FP extraction performance, we compare the proposed method with a method based on partially collapsed Gibbs sampler and an established EKF-based method. The mean absolute error and the root mean square error of all FPs, across all databases are 14 ms and 22 ms, respectively, for our proposed method, with an advantage when using a nonlinear phase observation. These errors are significantly smaller than errors obtained with other methods. For ECG interval analysis, with an absolute mean error and a root mean square error of about 22 ms and 29 ms, the proposed method achieves better accuracy and smaller variability with respect to other methods.

Multimodal approach to estimate the ocular movements during EEG recordings: A coupled tensor factorization method.

This paper deals with coupled tensor factorization. A relaxed criterion derived from the advanced coupled matrix-tensor factorization (ACMTF) proposed by Acar et al. is described. The proposed relaxed ACMTF (RACMTF) criterion is based on weaker assumptions that are thus more often satisfied when dealing with actual data. Numerical simulations show the benefit of using jointly two data sets when the underlying factors are highly correlated, especially if one of the modality is less noisy than the other one. The proposed method is finally applied on actual Gaze&EEG data to estimate the ocular artifacts into the EEG recordings.

Touch increases autonomic coupling between romantic partners.

Interpersonal touch is of paramount importance in human social bonding and close relationships, allowing a unique channel for affect communication. So far the effect of touch on human physiology has been studied at an individual level. The present study aims at extending the study of affective touch from isolated individuals to truly interacting dyads. We have designed an ecological paradigm where romantic partners interact only via touch and we manipulate their empathic states. Simultaneously, we collected their autonomic activity (skin conductance, pulse, respiration). Fourteen couples participated to the experiment. We found that interpersonal touch increased coupling of electrodermal activity between the interacting partners, regardless the intensity and valence of the emotion felt. In addition, physical touch induced strong and reliable changes in physiological states within individuals. These results support an instrumental role of interpersonal touch for affective support in close relationships. Furthermore, they suggest that touch alone allows the emergence of a somatovisceral resonance between interacting individuals, which in turn is likely to form the prerequisites for emotional contagion and empathy.

Modeling quasi-periodic signals by a non-parametric model: application on fetal ECG extraction.

Quasi-periodic signals can be modeled by their second order statistics as Gaussian process. This work presents a non-parametric method to model such signals. ECG, as a quasi-periodic signal, can also be modeled by such method which can help to extract the fetal ECG from the maternal ECG signal, using a single source abdominal channel. The prior information on the signal shape, and on the maternal and fetal RR interval, helps to better estimate the parameters while applying the Bayesian principles. The values of the parameters of the method, among which the R-peak instants, are accurately estimated using the Metropolis-Hastings algorithm. This estimation provides very precise values for the R-peaks, so that they can be located even between the existing time samples.

Non-local mind from the perspective of social cognition.

Two main conceptual approaches have been employed to study the mechanisms of social cognition, whether one considers isolated or interacting minds. Using neuro-imaging of subjects in isolation, the former approach has provided knowledge on the neural underpinning of a variety of social processes. However, it has been argued that considering one brain alone cannot account for all mechanisms subtending online social interaction. This challenge has been tackled recently by using neuro-imaging of multiple interacting subjects in more ecological settings. The present short review aims at offering a comprehensive view on various advances done in the last decade. We provide a taxonomy of existing research in neuroscience of social interaction, situating them in the frame of general organization principles of social cognition. Finally, we discuss the putative enabling role of emerging non-local social mechanisms-such as interpersonal brain and body coupling-in processes underlying our ability to create a shared world.

Reference-based source separation method for identification of brain regions involved in a reference state from intracerebral EEG.

In this paper, we present a fast method to extract the sources related to interictal epileptiform state. The method is based on general eigenvalue decomposition using two correlation matrices during: 1) periods including interictal epileptiform discharges (IED) as a reference activation model and 2) periods excluding IEDs or abnormal physiological signals as background activity. After extracting the most similar sources to the reference or IED state, IED regions are estimated by using multiobjective optimization. The method is evaluated using both realistic simulated data and actual intracerebral electroencephalography recordings of patients suffering from focal epilepsy. These patients are seizure-free after the resective surgery. Quantitative comparisons of the proposed IED regions with the visually inspected ictal onset zones by the epileptologist and another method of identification of IED regions reveal good performance.

Fetal ECG extraction by extended state Kalman filtering based on single-channel recordings.

In this paper, we present an extended nonlinear Bayesian filtering framework for extracting electrocardiograms (ECGs) from a single channel as encountered in the fetal ECG extraction from abdominal sensor. The recorded signals are modeled as the summation of several ECGs. Each of them is described by a nonlinear dynamic model, previously presented for the generation of a highly realistic synthetic ECG. Consequently, each ECG has a corresponding term in this model and can thus be efficiently discriminated even if the waves overlap in time. The parameter sensitivity analysis for different values of noise level, amplitude, and heart rate ratios between fetal and maternal ECGs shows its effectiveness for a large set of values of these parameters. This framework is also validated on the extractions of fetal ECG from actual abdominal recordings, as well as of actual twin magnetocardiograms.