Enhanced Data Covariance Estimation Using Weighted Combination of Multiple Gaussian Kernels for Improved M/EEG Source Localization

In the recent past, estimating brain activity with magneto/electroencephalography (M/EEG) has been increasingly employed as a noninvasive technique for understanding the brain functions and neural dynamics. However, one of the main open problems when dealing with M/EEG data is its non-Gaussian and nonstationary structure. In this paper, we introduce a methodology for enhancing the data covariance estimation using a weighted combination of multiple Gaussian kernels, termed WM-MK, that relies on the Kullback-Leibler divergence for associating each kernel weight to its relevance. From the obtained results of validation on nonstationary and non-Gaussian brain activity (simulated and real-world EEG data), WM-MK proves that the accuracy of the source estimation raises by more effectively exploiting the measured nonlinear structures with high time and space complexity.

[1]  Francesco Carlo Morabito,et al.  Permutation Disalignment Index as an Indirect, EEG-Based, Measure of Brain Connectivity in MCI and AD Patients , 2017, Int. J. Neural Syst..

[2]  G Castellanos-Dominguez,et al.  Reconstruction of Neural Activity from EEG Data Using Dynamic Spatiotemporal Constraints , 2016, Int. J. Neural Syst..

[3]  J.C. Mosher,et al.  Multiple dipole modeling and localization from spatio-temporal MEG data , 1992, IEEE Transactions on Biomedical Engineering.

[4]  Karl J. Friston,et al.  Multiple sparse priors for the M/EEG inverse problem , 2008, NeuroImage.

[5]  Karl J. Friston,et al.  A Parametric Empirical Bayesian framework for fMRI‐constrained MEG/EEG source reconstruction , 2010, Human brain mapping.

[6]  Hamid Reza Mohseni,et al.  Non-Gaussian probabilistic MEG source localisation based on kernel density estimation☆ , 2014, NeuroImage.

[7]  Bin He,et al.  EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks , 2016, IEEE Transactions on Biomedical Engineering.

[8]  Karl J. Friston,et al.  Algorithmic procedures for Bayesian MEG/EEG source reconstruction in SPM , 2014, NeuroImage.

[9]  Thomas Gärtner,et al.  A survey of kernels for structured data , 2003, SKDD.

[10]  Bart Vanrumste,et al.  Review on solving the forward problem in EEG source analysis , 2007, Journal of NeuroEngineering and Rehabilitation.

[11]  David P. Wipf,et al.  A unified Bayesian framework for MEG/EEG source imaging , 2009, NeuroImage.

[12]  Karl J. Friston,et al.  Variational free energy and the Laplace approximation , 2007, NeuroImage.

[13]  Richard N Henson,et al.  A multi-subject, multi-modal human neuroimaging dataset , 2015, Scientific Data.

[14]  Stefan Haufe,et al.  Solving the EEG inverse problem based on space–time–frequency structured sparsity constraints , 2015, NeuroImage.

[15]  Michel Verleysen,et al.  Kernel-based dimensionality reduction using Renyi's α-entropy measures of similarity , 2017, Neurocomputing.

[16]  Yusuf Uzzaman Khan,et al.  A Wavelet-Statistical Features Approach for Nonconvulsive Seizure Detection , 2014, Clinical EEG and neuroscience.

[17]  Lei Wang,et al.  Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[18]  Jesús Francisco Vargas-Bonilla,et al.  Non-linear Covariance Estimation for Reconstructing Neural Activity with MEG/EEG Data , 2017, IWINAC.

[19]  A. Dale,et al.  Improved Localizadon of Cortical Activity by Combining EEG and MEG with MRI Cortical Surface Reconstruction: A Linear Approach , 1993, Journal of Cognitive Neuroscience.

[20]  Ethem Alpaydin,et al.  Multiple Kernel Learning Algorithms , 2011, J. Mach. Learn. Res..

[21]  Alexandre Gramfort,et al.  Automated model selection in covariance estimation and spatial whitening of MEG and EEG signals , 2015, NeuroImage.

[22]  Andrés Marino Álvarez-Meza,et al.  Unsupervised Kernel Function Building Using Maximization of Information Potential Variability , 2014, CIARP.

[23]  Yu Huang,et al.  The New York Head—A precise standardized volume conductor model for EEG source localization and tES targeting , 2015, NeuroImage.

[24]  H. Adeli,et al.  Wavelet Coherence Model for Diagnosis of Alzheimer Disease , 2012, Clinical EEG and neuroscience.

[25]  Karl J. Friston,et al.  Electromagnetic source reconstruction for group studies , 2008, NeuroImage.

[26]  Richard M. Leahy,et al.  Matrix kernels for MEG and EEG source localization and imaging , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[27]  Bart Vanrumste,et al.  Journal of Neuroengineering and Rehabilitation Open Access Review on Solving the Inverse Problem in Eeg Source Analysis , 2022 .

[28]  David Poeppel,et al.  Reconstructing spatio-temporal activities of neural sources using an MEG vector beamformer technique , 2001, IEEE Transactions on Biomedical Engineering.

[29]  U. Rajendra Acharya,et al.  Shear wave elastography for characterization of breast lesions: Shearlet transform and local binary pattern histogram techniques , 2017, Comput. Biol. Medicine.

[30]  Hamid Reza Mohseni,et al.  Dynamic state allocation for MEG source reconstruction , 2013, NeuroImage.

[31]  Hong Yu,et al.  Local density adaptive similarity measurement for spectral clustering , 2011, Pattern Recognit. Lett..

[32]  Hamid Reza Mohseni,et al.  A new beamforming-based MEG dipole source localization method , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[33]  Pieter van Mierlo,et al.  Improved Localization of Seizure Onset Zones Using Spatiotemporal Constraints and Time-Varying Source Connectivity , 2017, Front. Neurosci..

[34]  Jose L. Contreras-Vidal,et al.  Multiple Kernel Based Region Importance Learning for Neural Classification of Gait States from EEG Signals , 2017, Front. Neurosci..

[35]  Mauricio A. Álvarez,et al.  Kernel temporal enhancement approach for LORETA source reconstruction using EEG data , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[36]  Kaizhu Huang,et al.  Enhanced protein fold recognition through a novel data integration approach , 2009, BMC Bioinformatics.

[37]  Lennart Ljung,et al.  Kernel methods in system identification, machine learning and function estimation: A survey , 2014, Autom..

[38]  Saeid Sanei,et al.  Detection of Intracranial Signatures of Interictal Epileptiform Discharges from Concurrent Scalp EEG , 2016, Int. J. Neural Syst..