Wassim Zouch

Spatial Resolution Improvement of EEG Source Reconstruction Using swLORETA

Electroencephalography (EEG) and magnetic resonance imaging (MRI) are noninvasive neuro-imaging modalities largely used in neurology explorations. MRI is considered as a static modality and could be so important for anatomy by its high spatial resolution. EEG, on the other hand, is an important tool permitting to image temporal dynamic activities of the human brain. Fusion of these two essential modalities would be hence a so emerging research domain targeting to explore brain activities with the MRI static modality. Our present research investigates a sophisticated approach for localization of the cerebral activity that could be involved by the dynamic EEG modality and carefully illustrated within MRI static modality. Such careful cerebral activity localization would be first based on an advanced methodology yielding therefore a singular value decomposition-based lead field weighting to sLORETA method formalism, for solving in fact the inverse problem in the EEG. The conceived method for source localization, carried out on different cases of simulated dipoles experiments, showed satisfactory results. Different cases of simulated dipoles experiments and metrics were used to confirm the reliability of the proposed method. The experimental results confirm that our method presents a flexible and robust tool for EEG source imaging.

A comparison study of SSVEP detection methods using the Emotiv Epoc headset

Recently, the low cost EEG acquisition systems such as the Emotiv Epoc give new tools to develop Brain-Computer interface systems for everyday use outside the laboratory. However, the low sampling rate and the low number of channels remain possible sources of failure. The Canonical Correlation Analysis and the Multivariate Synchronization Index (MSI) methods are applied in a SSVEP-based BCI in order to compare their accuracies. The main goal of this research is to find the appropriate method allowing the control of an autonomous wheelchair by the severely handicapped people. The experimental results show that the MSI method reaches 96% of accuracy with optimal parameters.

A bayesian approach for EEG inverse problem: Spatio-temporal regularization

The famous inverse problem in EEG (electroencephalography) is an ill-posed problem. Its priors or constraints are required to ensure getting an unique solution. Moreover, added to spatial constraints, we impose temporal smoothness priors on dipole magnitude. These constraints are easily included into a Bayesian formalism, through a maximum a posteriori “MAP estimator” of electrical density in the brain. We used a simulated dipole experiment to explore the behavior of our approach with and without temporal constraints.

Brief review of multiple sclerosis lesions segmentation methods on conventional magnetic resonance imaging

Multiple sclerosis is a chronic inflammatory disease of the central nervous system. Lesions detected by Magnetic resonance (MR) sequences not only confirme the diagnosis of MS, but let monitor them to determine the evolutionary state of the disease and to evaluate the therapeutic efficiency. Thus, the change in lesion load is a criterion determining the degree of progress of the disease in volume, shape and location. For this purpose, a segmentation of these lesions becomes paramount. Some recent methods of semiautomatic and automatic segmentation have been proposed to get rid of complex and laborious manual segmentation. Subsequently, the variability inter and intra-experts will be reduced. The purpose of this study is to accomplish a brief review of MS lesions segmentation methods proposed in the literature.

LORETA solution for spatio-temporal EEG source reconstruction

In this paper, we presented the famous method called Low resolution brain electromagnetic tomography (LORETA) used for the localization of neural electrical current. This method is used to solve the EEG (electroencephalography) inverse problems. In this study, we focused on the localization accuracy and time behavior of the LORETA method. Therefore, this method is tested using three simulated dipole configurations; single dipole, two distinct dipoles and one moving dipole. After that, the effect of the time component is highlighted on the localization accuracy and the importance of taking the maximum or average activity during our time window in the distinction peaks of activity.

Frequency recognition based on the Inter-Battery Factor Analysis for SSVEP-based BCIs

The Brain-Computer Interface is a system mainly designed to provide people suffering from severe neuromuscular disorder with a new mean of communication and control. Increasing the system accuracy rate is the goal of several studies. In fact, ameliorating this criterion allows to minimize the correction phase and makes the use of the system more natural. This is very important to develop Brain-Computer interface systems for everyday use outside the laboratory. This paper introduces a new Brain-Computer Interface based on the Inter-Battery Factor Analysis method. The results show that the proposed BCI system has a higher accuracy than systems based on Canonical Correlation Analysis or Multivariate Synchronization Index. The accuracy rate has reached 93.2% for the five participants using only the two electrodes O1 and O2 with data acquired over a period of 2.25s.

Anti-noise Capability Improvement of Minimum Energy Combination Method for SSVEP Detection

Minimum energy combination (MEC) is a widely used method for frequency recognition in steady state visual evoked potential based BCI systems. Although it can reach acceptable performances, this method remains sensitive to noise. This paper introduces a new technique for the improvement of the MEC method allowing ameliorating its Anti-noise capability. The Empirical mode decomposition (EMD) and the moving average filter were used to separate noise from relevant signals. The results show that the proposed BCI system has a higher accuracy than systems based on Canonical Correlation Analysis (CCA) or Multivariate Synchronization Index (MSI). In fact, the system achieves an average accuracy of about 99% using real data measured from five subjects by means of the EPOC EMOTIVE headset with three visual stimuli. Also by using four commands, the system accuracy reaches 91.78% with an information-transfer rate of about 27.18 bits/min.

High-resolution imaging-guided electroencephalography source localization: temporal effect regularization incorporation in LORETA inverse solution

Abstract. Electroencephalography (EEG) and magnetic resonance imaging (MRI) are noninvasive neuroimaging modalities. They are widely used and could be complementary. The fusion of these modalities may enhance some emerging research fields targeting the exploration better brain activities. Such research attracted various scientific investigators especially to provide a convivial and helpful advanced clinical-aid tool enabling better neurological explorations. Our present research was, in fact, in the context of EEG inverse problem resolution and investigated an advanced estimation methodology for the localization of the cerebral activity. Our focus was, therefore, on the integration of temporal priors to low-resolution brain electromagnetic tomography (LORETA) formalism and to solve the inverse problem in the EEG. The main idea behind our proposed method was in the integration of a temporal projection matrix within the LORETA weighting matrix. A hyperparameter is the principal fact for such a temporal integration, and its importance would be obvious when obtaining a regularized smoothness solution. Our experimental results clearly confirmed the impact of such an optimization procedure adopted for the temporal regularization parameter comparatively to the LORETA method.

PGVF-ACM automatic segmentation of PET images for breast cancer characterization

Medical imaging research became an important field of investigation that could be very useful for clinical exploration, particularly for serious pathological cases such as cancer. In this proposed clinical aided tool, we were interested at the moment in analysis and exploration for standard segmentation of Positron Emission Tomography (PET) images for the breast cancer characterization. This research was hence established between technological team and clinical team in order to design a convivial platform, flexible and directly usable by clinicians for tumor tissue diagnosis and exploration. Particular attention will be given to breast cancer that threatens an important number of patients in the world. Such serious pathology could be carefully imaged by PET technology. The work was based on two proposed and combined approaches for the automatic segmentation of PET images: Poisson Gradient Vector Flow Active Contour Model <; PGVF-ACM > with and without implanting one dedicated Genetic Algorithm. Our objective in this research was mainly to compare these two approaches for this proposed application that could be very useful for clinical exploration. Experimental results for our PGVFACM automatic segmentation for several PET images were significant and demonstrate the effectiveness of the Genetic Algorithm that was applied to optimize automatically both threshold and sigma parameters.