ICA-based EEG denoising: a comparative analysis of fifteen methods

Independent Component Analysis (ICA) plays an important role in biomedical engineering. Indeed, the complexity of processes involved in biomedicine and the lack of reference signals make this blind approach a powerful tool to extract sources of interest. However, in practice, only a few ICA algorithms such as SOBI, (extended) InfoMax and FastICA are used nowadays to process biomedical signals. In this paper we raise the question whether other ICA methods could be better suited in terms of performance and computational complexity. We focus on ElectroEncephaloGraphy (EEG) data denoising, and more particularly on removal of muscle artifacts from interictal epileptiform activity. Assumptions required by ICA are discussed in such a context. Then fifteen ICA algorithms, namely JADE, CoM2, SOBI, SOBIrob, (extended) InfoMax, PICA, two different implementations of FastICA, ERICA, SIMBEC, FOBIUMJAD, TFBSS, ICAR3, FOOBI1 and 4-CANDHAPc are briefly described. Next they are studied in terms of performance and numerical complexity. Quantitative results are obtained on simulated epileptic data generated with a physiologically-plausible model. These results are also illustrated on real epileptic recordings.

[1]  E. Oja,et al.  BSS and ICA in Neuroinformatics: From Current Practices to Open Challenges , 2008, IEEE Reviews in Biomedical Engineering.

[2]  Fabrice Wendling,et al.  A Physiologically Plausible Spatio-Temporal Model for EEG Signals Recorded With Intracerebral Electrodes in Human Partial Epilepsy , 2007, IEEE Transactions on Biomedical Engineering.

[3]  Laurent Albera,et al.  Joint Eigenvalue Decomposition Using Polar Matrix Factorization , 2010, LVA/ICA.

[4]  Marissa Westerfield,et al.  INDEPENDENT COMPONENT ANALYSIS OF SINGLE-TRIAL EVENT-RELATED POTENTIALS , 1999 .

[5]  Fabrice Wendling,et al.  Computational Modeling of Epileptic Activity: From Cortical Sources to EEG Signals , 2010, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[6]  Richard J. Davidson,et al.  Validation of ICA-based myogenic artifact correction for scalp and source-localized EEG , 2010, NeuroImage.

[7]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[8]  J. Sarvas.  Basic mathematical and electromagnetic concepts of the biomagnetic inverse problem. , 1987, Physics in medicine and biology.

[9]  Eric Moreau,et al.  Criteria for complex sources separation , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

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

[11]  Fetsje Bijma,et al.  In vivo measurement of the brain and skull resistivities using an EIT-based method and realistic models for the head , 2003, IEEE Transactions on Biomedical Engineering.

[12]  Laurent Albera,et al.  ICAR: independent component analysis using redundancies , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[13]  Laurent Albera,et al.  Fourth-order blind identification of underdetermined mixtures of sources (FOBIUM) , 2005, IEEE Transactions on Signal Processing.

[14]  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.

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

[16]  Tony F. Chan,et al.  An Improved Algorithm for Computing the Singular Value Decomposition , 1982, TOMS.

[17]  L. De Lathauwer,et al.  Canonical decomposition of even higher order cumulant arrays for blind underdetermined mixture identification , 2008, 2008 5th IEEE Sensor Array and Multichannel Signal Processing Workshop.

[18]  P. Comon,et al.  Tensor decompositions, alternating least squares and other tales , 2009 .

[19]  José Millet-Roig,et al.  Atrial activity extraction for atrial fibrillation analysis using blind source separation , 2004, IEEE Transactions on Biomedical Engineering.

[20]  P. Comon,et al.  Ica: a potential tool for bci systems , 2008, IEEE Signal Processing Magazine.

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

[22]  Andrzej Cichocki,et al.  Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis , 2002, Biological Cybernetics.

[23]  Laurent Albera,et al.  Localization of extended brain sources from EEG/MEG: The ExSo-MUSIC approach , 2011, NeuroImage.

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

[25]  Christian Sander,et al.  ICA-based muscle artefact correction of EEG data: What is muscle and what is brain? Comment on McMenamin et al. , 2011, NeuroImage.

[26]  Gene H. Golub,et al.  Singular value decomposition and least squares solutions , 1970, Milestones in Matrix Computation.

[27]  Pierre Comon,et al.  Séparation de mélanges de signaux , 1989 .

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

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

[30]  Laurent Albera,et al.  Iterative methods for the canonical decomposition of multi-way arrays: Application to blind underdetermined mixture identification , 2011, Signal Process..

[31]  Terrence J. Sejnowski,et al.  Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources , 1999, Neural Computation.

[32]  Erkki Oja,et al.  Efficient Variant of Algorithm FastICA for Independent Component Analysis Attaining the CramÉr-Rao Lower Bound , 2006, IEEE Transactions on Neural Networks.

[33]  Pierre Comon,et al.  Handbook of Blind Source Separation: Independent Component Analysis and Applications , 2010 .

[34]  Lotfi Senhadji,et al.  Blind source separation for ambulatory sleep recording , 2006, IEEE Transactions on Information Technology in Biomedicine.

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

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

[37]  P. McCullagh.  Tensor Methods in Statistics , 1987 .

[38]  Terrence J. Sejnowski,et al.  Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Sub-Gaussian and Super-Gaussian Sources , 1999, Neural Comput..

[39]  Fabrice Wendling,et al.  Relevance of nonlinear lumped-parameter models in the analysis of depth-EEG epileptic signals , 2000, Biological Cybernetics.

[40]  Erkki Oja,et al.  Independent component approach to the analysis of EEG and MEG recordings , 2000, IEEE Transactions on Biomedical Engineering.

[41]  Christian Jutten,et al.  Overview of source separation applications , 2010 .

[42]  Lieven De Lathauwer,et al.  Blind Identification of Underdetermined Mixtures by Simultaneous Matrix Diagonalization , 2008, IEEE Transactions on Signal Processing.

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

[44]  Visa Koivunen,et al.  Blind separation methods based on Pearson system and its extensions , 2002, Signal Process..

[45]  Lieven De Lathauwer,et al.  Fourth-Order Cumulant-Based Blind Identification of Underdetermined Mixtures , 2007, IEEE Transactions on Signal Processing.

[46]  Amar Kachenoura,et al.  Séparation aveugle de sources en ingénierie biomédicale , 2007 .

[47]  Sergio Cruces,et al.  On a new blind signal extraction algorithm: different criteria and stability analysis , 2002, IEEE Signal Processing Letters.

[48]  Cédric Févotte,et al.  Two contributions to blind source separation using time-frequency distributions , 2004, IEEE Signal Processing Letters.

[49]  P. Comon,et al.  ICAR: a tool for blind source separation using fourth-order statistics only , 2005, IEEE Transactions on Signal Processing.

[50]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[51]  Tzyy-Ping Jung,et al.  Extended ICA Removes Artifacts from Electroencephalographic Recordings , 1997, NIPS.

[52]  Albert N. Shiryaev,et al.  On a Method of Calculation of Semi-Invariants , 1959 .

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

[54]  Sergio Cruces,et al.  Novel blind source separation algorithms using cumulants , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[55]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.