Contribution à la détection et à l'analyse des signaux EEG épileptiques : débruitage et séparation de sources

L'objectif principal de cette these est le pre-traitement des signaux d'electroencephalographie (EEG). En particulier, elle vise a developper une methodologie pour obtenir un EEG dit "propre" a travers l'identification et l'elimination des artefacts extra-cerebraux (mouvements oculaires, clignements, activite cardiaque et musculaire) et du bruit. Apres identification, les artefacts et le bruit doivent etre elimines avec une perte minimale d'information, car dans le cas d'EEG, il est de grande importance de ne pas perdre d'information potentiellement utile a l'analyse (visuelle ou automatique) et donc au diagnostic medical. Plusieurs etapes sont necessaires pour atteindre cet objectif : separation et identification des sources d'artefacts, elimination du bruit de mesure et reconstruction de l'EEG "propre". A travers une approche de type separation aveugle de sources (SAS), la premiere partie vise donc a separer les signaux EEG dans des sources informatives cerebrales et des sources d'artefacts extra-cerebraux a eliminer. Une deuxieme partie vise a classifier et eliminer les sources d'artefacts et elle consiste en une etape de classification supervisee. Le bruit de mesure, quant a lui, il est elimine par une approche de type debruitage par ondelettes. La mise en place d'une methodologie integrant d'une maniere optimale ces trois techniques (separation de sources, classification supervisee et debruitage par ondelettes) constitue l'apport principal de cette these. La methodologie developpee, ainsi que les resultats obtenus sur une base de signaux d'EEG reels (critiques et inter-critiques) importante, sont soumis a une expertise medicale approfondie, qui valide l'approche proposee.

[1]  Fabian J. Theis,et al.  Linear Geometric ICA: Fundamentals and Algorithms , 2003, Neural Computation.

[2]  Radu Ranta,et al.  Débruitage par ondelettes et segmentation de signaux non-stationnaires : réinterprétation d'un algorithme itératif et application à la phonoentérographie Wavelet denoising and segmentation for non-stationary signals : a reinterpretation of an iterative algorithm and application to phonoenterography , 2003 .

[3]  Y. Tran,et al.  Using independent component analysis to remove artifact from electroencephalographic measured during stuttered speech , 2004, Medical and Biological Engineering and Computing.

[4]  T. Sejnowski,et al.  Removing electroencephalographic artifacts by blind source separation. , 2000, Psychophysiology.

[5]  Gesamtverband Deutscher Nervenärzte European archives of psychiatry and clinical neuroscience , 1990 .

[6]  J. Spatt,et al.  Reliability of automatic and visual analysis of interictal spikes in lateralising an epileptic focus during video-EEG monitoring. , 1997, Electroencephalography and clinical neurophysiology.

[7]  Xianda Zhang,et al.  Sequential Blind Extraction Adopting Second-Order Statistics , 2007, IEEE Signal Processing Letters.

[8]  S. Amari,et al.  CRITERIA FOR THE SIMULTANEOUS BLIND EXTRACTION OF ARBITRARY GROUPS OF SOURCES , 2001 .

[9]  Yannick Deville,et al.  Panorama des applications biomédicales des méthodes de séparation aveugle de sources , 2003 .

[10]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[11]  Olivier Sibony,et al.  Fetal electrocardiogram extraction based on non-stationary ICA and wavelet denoising , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[12]  P. Tichavský,et al.  Efficient variant of algorithm fastica for independent component analysis attaining the cramer-RAO lower bound , 2005, IEEE/SP 13th Workshop on Statistical Signal Processing, 2005.

[13]  Joep J. M. Kierkels,et al.  A model-based objective evaluation of eye movement correction in EEG recordings , 2006, IEEE Transactions on Biomedical Engineering.

[14]  Shuxue Ding,et al.  A Power Iteration Algorithm for ICA Based on Diagonalizations of Non-Linearized Covariance Matrix , 2006, First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06).

[15]  Seungjin Choi,et al.  Independent Component Analysis , 2009, Handbook of Natural Computing.

[16]  Christopher J. James,et al.  Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis , 2003, IEEE Transactions on Biomedical Engineering.

[17]  Xi-Lin Li,et al.  Nonorthogonal Joint Diagonalization Free of Degenerate Solution , 2007, IEEE Transactions on Signal Processing.

[18]  P. Philips,et al.  JADETD : COMBINING HIGHER-ORDER STATISTICS AND TEMPORALINFORMATION FOR BLIND SOURCE SEPARATION ( WITH NOISE ) , 1999 .

[19]  Antoine Souloumiac,et al.  Jacobi Angles for Simultaneous Diagonalization , 1996, SIAM J. Matrix Anal. Appl..

[20]  Westen Drew,et al.  Psychologie : Pensée, cerveau et culture , 2000 .

[21]  D. L. Donoho,et al.  Ideal spacial adaptation via wavelet shrinkage , 1994 .

[22]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[23]  R. Ranta,et al.  EEG Ocular Artefacts and Noise Removal , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Andrzej Cichocki,et al.  Blind source separation via symmetric eigenvalue decomposition , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).

[25]  Cédric Févotte,et al.  Approche temps-fréquence pour la séparation aveugle de sources non-stationnaires , 2003 .

[26]  V. A. Makarov,et al.  Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis , 2006, Journal of Neuroscience Methods.

[27]  A. Cichocki,et al.  Robust whitening procedure in blind source separation context , 2000 .

[28]  Détection et classification d'événements en représentation multidimensionnelle. Application sur l'EMG utérin , 1997 .

[29]  C. Joyce,et al.  Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. , 2004, Psychophysiology.

[30]  Kenzo Akazawa,et al.  INDEPENDENT COMPONENT ANALYSIS AS PREPROCESSING TOOL FOR DECOMPOSITION OF SURFACE ELECTRODE-ARRAY ELECTROMYOGRAM , 2003 .

[31]  F. Wendling,et al.  Temporal lobe epilepsy , 2019, Radiopaedia.org.

[32]  Sergio Cruces,et al.  Blind source extraction in Gaussian noise , 2000 .

[33]  Fabrice Wendling,et al.  The neuronal sources of EEG: Modeling of simultaneous scalp and intracerebral recordings in epilepsy , 2008, NeuroImage.

[34]  K H Ting,et al.  Automatic correction of artifact from single-trial event-related potentials by blind source separation using second order statistics only. , 2006, Medical engineering & physics.

[35]  Ronald R. Coifman,et al.  Experiments with Adapted Wavelet De-Noising for Medical Signals and Images , 1995 .

[36]  Michael Unser,et al.  A review of wavelets in biomedical applications , 1996, Proc. IEEE.

[37]  Didier Maquin,et al.  Ocular artifacts removal in scalp EEG: combining ICA and wavelett denoising , 2007 .

[38]  Christian Vasseur,et al.  Filtering by optimal projection and application to automatic artifact removal from EEG , 2007, Signal Process..

[39]  R. Williams,et al.  The control of neuron number. , 1988, Annual review of neuroscience.

[40]  Percival Bailey L'exploration chirurgicale stéréotaxique du lobe temporal dans l'épilepsie temporale. , 1959 .

[41]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[42]  Asoke K. Nandi,et al.  Foetal ECG extraction using blind source separation methods , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[43]  Scott Makeig,et al.  Information-based modeling of event-related brain dynamics. , 2006, Progress in brain research.

[44]  Christian Jutten,et al.  Source separation in post-nonlinear mixtures , 1999, IEEE Trans. Signal Process..

[45]  J. Bellanger,et al.  Interpretation of interdependencies in epileptic signals using a macroscopic physiological model of the EEG , 2001, Clinical Neurophysiology.

[46]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[47]  Jean-Franois Cardoso High-Order Contrasts for Independent Component Analysis , 1999, Neural Computation.

[48]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[49]  Anestis Antoniadis,et al.  Wavelet methods in statistics: Some recent developments and their applications , 2007, 0712.0283.

[50]  Stavros M. Panas,et al.  Enhancement of bowel sounds by wavelet-based filtering , 2000, IEEE Transactions on Biomedical Engineering.

[51]  Dario Farina,et al.  Blind separation of linear instantaneous mixtures of nonstationary surface myoelectric signals , 2004, IEEE Transactions on Biomedical Engineering.

[52]  A. Yeredor Blind separation of Gaussian sources via second-order statistics with asymptotically optimal weighting , 2000, IEEE Signal Processing Letters.

[53]  Vladimir Cherkassky,et al.  Comparison of Wavelet Thresholding Methods for Denoising ECG Signals , 2001, ICANN.

[54]  F. L. D. Silva,et al.  EEG signal processing , 2000, Clinical Neurophysiology.

[55]  É. Moulines,et al.  Second Order Blind Separation of Temporally Correlated Sources , 1993 .

[56]  C. Stein Estimation of the Mean of a Multivariate Normal Distribution , 1981 .

[57]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[58]  Didier Wolf,et al.  Iterative wavelet-based denoising methods and robust outlier detection , 2005, IEEE Signal Processing Letters.

[59]  F. Semah La TEP et la TEMP pour l’étude des épilepsies , 2007 .

[60]  P. Grassberger,et al.  A robust method for detecting interdependences: application to intracranially recorded EEG , 1999, chao-dyn/9907013.

[61]  Lang Tong,et al.  Indeterminacy and identifiability of blind identification , 1991 .

[62]  Dezhong Yao,et al.  A study on the reference electrode standardization technique for a realistic head model , 2004, Comput. Methods Programs Biomed..

[63]  Christian Jutten,et al.  On the blind source separation of human electroencephalogram by approximate joint diagonalization of second order statistics , 2008, Clinical Neurophysiology.

[64]  Seungjin Choi Blind Source Separation and Independent Component Analysis : A Review , 2004 .

[65]  G. A. Miller,et al.  Comparison of different cortical connectivity estimators for high‐resolution EEG recordings , 2007, Human brain mapping.

[66]  J. Bellanger,et al.  Neural networks involving the medial temporal structures in temporal lobe epilepsy , 2001, Clinical Neurophysiology.

[67]  Slawomir J. Nasuto,et al.  Automatic Artefact Removal from Event-related Potentials via Clustering , 2007, J. VLSI Signal Process..

[68]  D.B. Geselowitz,et al.  The zero of potential , 1998, IEEE Engineering in Medicine and Biology Magazine.

[69]  Te-Won Lee,et al.  Independent Component Analysis , 1998, Springer US.

[70]  K Ramadoss,et al.  Automatic Removal of Ocular Artifacts using JADE Algorithm and Neural Network , 2007 .

[71]  J. Gotman,et al.  A system for automatic artifact removal in ictal scalp EEG based on independent component analysis and Bayesian classification , 2006, Clinical Neurophysiology.

[72]  Radu Ranta,et al.  EEG Montage Analysis in Blind Source Separation , 2009 .

[73]  Wim Van Paesschen,et al.  Independent component analysis of single trial evoked brain reponses : is it reliable ? , 2005 .

[74]  Yanda Li,et al.  Automatic removal of the eye blink artifact from EEG using an ICA-based template matching approach , 2006, Physiological measurement.

[75]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[76]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[77]  Anestis Antoniadis,et al.  Wavelet Estimators in Nonparametric Regression: A Comparative Simulation Study , 2001 .

[78]  J Möcks,et al.  How to select epochs of the EEG at rest for quantitative analysis. , 1984, Electroencephalography and clinical neurophysiology.

[79]  C. Jutten,et al.  QUADRATIC DEPENDENCE MEASURE FOR NONLINEAR BLIND SOURCES SEPARATION , 2003 .

[80]  Tzyy-Ping Jung,et al.  Independent Component Analysis of Electroencephalographic Data , 1995, NIPS.

[81]  D. Cohen Magnetoencephalography: Evidence of Magnetic Fields Produced by Alpha-Rhythm Currents , 1968, Science.

[82]  Laura Astolfi,et al.  The Effect of Connectivity on EEG Rhythms, Power Spectral Density and Coherence Among Coupled Neural Populations: Analysis With a Neural Mass Model , 2008, IEEE Transactions on Biomedical Engineering.

[83]  V. Prasad,et al.  Denoising of Biological Signals Using Different Wavelet Based Methods and Their Comparison , 2008 .

[84]  F. Wendling Mise en correspondance d'observations eeg de profondeur pour la reconnaissance de signatures spatio-temporelles dans les crises d'epilepsie , 1996 .

[85]  A. Cichocki,et al.  Blind separation of nonstationary sources in noisy mixtures , 2000 .

[86]  Mostefa Mesbah,et al.  A Nonstationary Model of Newborn EEG , 2007, IEEE Transactions on Biomedical Engineering.

[87]  Bellanger,et al.  6 - Détection temps-échelle d'évènements paroxystiques intercritiques en électroencéphalogramme , 1995 .

[88]  J. Fermaglich Electric Fields of the Brain: The Neurophysics of EEG , 1982 .

[89]  T. Sejnowski,et al.  Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects , 2000, Clinical Neurophysiology.

[90]  Peter Gruber,et al.  Automatic removal of high-amplitude artefacts from single-channel electroencephalograms , 2006, Comput. Methods Programs Biomed..

[91]  Miguel Angel Mañanas,et al.  A comparative study of automatic techniques for ocular artifact reduction in spontaneous EEG signals based on clinical target variables: A simulation case , 2008, Comput. Biol. Medicine.

[92]  Andreas Ziehe,et al.  TDSEP { an e(cid:14)cient algorithm for blind separation using time structure , 1998 .

[93]  Fabrice Wendling,et al.  Source localization of scalp‐EEG interictal spikes in posterior cortex epilepsies investigated by HR‐EEG and SEEG , 2009, Epilepsia.

[94]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[95]  R.N.Dej.,et al.  Epilepsy and the Functional Anatomy of the Human Brain , 1954, Neurology.

[96]  Shoji Makino,et al.  Blind source separation of convolutive mixtures , 2006, SPIE Defense + Commercial Sensing.

[97]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[98]  El Mostafa Fadaili,et al.  Nonorthogonal Joint Diagonalization/Zero Diagonalization for Source Separation Based on Time-Frequency Distributions , 2007, IEEE Transactions on Signal Processing.

[99]  Klaus Obermayer,et al.  Quadratic optimization for simultaneous matrix diagonalization , 2006, IEEE Transactions on Signal Processing.

[100]  Rebeca Romo-Vázquez,et al.  Connectivity estimation of scalp electrodes after preprocessing. Application to seizure detection. , 2009 .

[101]  Terrence J. Sejnowski,et al.  AUTOMATIC ARTIFACT REJECTION FOR EEG DATA USING HIGH-ORDER STATISTICS AND INDEPENDENT COMPONENT ANALYSIS , 2001 .

[102]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[103]  R N Vigário,et al.  Extraction of ocular artefacts from EEG using independent component analysis. , 1997, Electroencephalography and clinical neurophysiology.

[104]  C. Li,et al.  Detection of ECG characteristic points using wavelet transforms. , 1995, IEEE transactions on bio-medical engineering.

[105]  Barak A. Pearlmutter,et al.  Blind Source Separation by Sparse Decomposition in a Signal Dictionary , 2001, Neural Computation.

[106]  Sergio Cruces,et al.  COMBINING BLIND SOURCE EXTRACTION WITH JOINT APPROXIMATE DIAGONALIZATION: THIN ALGORITHMS FOR ICA , 2003 .

[107]  R. Kass,et al.  Automatic correction of ocular artifacts in the EEG: a comparison of regression-based and component-based methods. , 2004, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[108]  Sanqing Hu,et al.  Automatic Identification and Removal of Scalp Reference Signal for Intracranial EEGs Based on Independent Component Analysis , 2007, IEEE Transactions on Biomedical Engineering.

[109]  F. Perrin,et al.  Spherical splines for scalp potential and current density mapping. , 1989, Electroencephalography and clinical neurophysiology.

[110]  Andrzej Cichocki,et al.  Second Order Nonstationary Source Separation , 2002, J. VLSI Signal Process..

[111]  Erkki Oja,et al.  Independent Component Analysis for Identification of Artifacts in Magnetoencephalographic Recordings , 1997, NIPS.

[112]  T. Sejnowski,et al.  Single-Trial Variability in Event-Related BOLD Signals , 2002, NeuroImage.

[113]  Arie Yeredor,et al.  Blind signal separation by combining two ICA algorithms: HOS-based EFICA and time structure-based WASOBI , 2006, 2006 14th European Signal Processing Conference.

[114]  Ronald R. Coifman,et al.  Adapted waveform "de-noising" for medical signals and images , 1995 .

[115]  Aapo Hyvärinen,et al.  Independent component analysis of fMRI group studies by self-organizing clustering , 2005, NeuroImage.

[116]  Laura Astolfi,et al.  Tracking the Time-Varying Cortical Connectivity Patterns by Adaptive Multivariate Estimators , 2008, IEEE Transactions on Biomedical Engineering.

[117]  T. Ens,et al.  Blind signal separation : statistical principles , 1998 .

[118]  Francesco Carlo Morabito,et al.  Kurtosis, Renyi's Entropy and Independent Component Scalp Maps for the Automatic Artifact Rejection from EEG data , 2008 .

[119]  Joos Vandewalle,et al.  Fetal electrocardiogram extraction by blind source subspace separation , 2000, IEEE Transactions on Biomedical Engineering.

[120]  J. Bellanger,et al.  Interictal to Ictal Transition in Human Temporal Lobe Epilepsy: Insights From a Computational Model of Intracerebral EEG , 2005, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[121]  You Rong-yi,et al.  Blind source separation of multichannel electroencephalogram based on wavelet transform and ICA , 2005 .

[122]  Derek Abbott,et al.  Techniques for noise removal from EEG, EOG, and airflow signals in sleep patients , 2004, SPIE International Symposium on Fluctuations and Noise.

[123]  Ricardo Vigário,et al.  Overlearning in Marginal Distribution-Based ICA: Analysis and Solutions , 2003, J. Mach. Learn. Res..

[124]  C. Jutten,et al.  L'Analyse en Composantes Indépendantes : un outil puissant pour le traitement de l'information , 2003 .

[125]  Christian Jutten,et al.  Wavelet De-noising for Blind Source Separation in Noisy Mixtures , 2004, ICA.

[126]  J. Blau Color Atlas of Neuroscience. Neuroanatomy and Neurophysiology , 2000 .