Fast robust subject‐independent magnetoencephalographic source localization using an artificial neural network

We describe a system that localizes a single dipole to reasonable accuracy from noisy magnetoencephalographic (MEG) measurements in real time. At its core is a multilayer perceptron (MLP) trained to map sensor signals and head position to dipole location. Including head position overcomes the previous need to retrain the MLP for each subject and session. The training dataset was generated by mapping randomly chosen dipoles and head positions through an analytic model and adding noise from real MEG recordings. After training, a localization took 0.7 ms with an average error of 0.90 cm. A few iterations of a Levenberg‐Marquardt routine using the MLP output as its initial guess took 15 ms and improved accuracy to 0.53 cm, which approaches the natural limit on accuracy imposed by noise. We applied these methods to localize single dipole sources from MEG components isolated by blind source separation and compared the estimated locations to those generated by standard manually assisted commercial software. Hum. Brain Mapping 24:21–34, 2005. © 2004 Wiley‐Liss, Inc.

[1]  L. Parkkonen,et al.  122-channel squid instrument for investigating the magnetic signals from the human brain , 1993 .

[2]  Barak A. Pearlmutter,et al.  Independent components of magnetoencephalography: Localization and single-trial response onset detection , 2002 .

[3]  G Van Hoey,et al.  EEG dipole source localization using artificial neural networks. , 2000, Physics in medicine and biology.

[4]  Udantha R. Abeyratne,et al.  Artificial neural networks for source localization in the human brain , 2005, Brain Topography.

[5]  T. Sejnowski,et al.  Functionally Independent Components of the Late Positive Event-Related Potential during Visual Spatial Attention , 1999, The Journal of Neuroscience.

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

[7]  Yann LeCun,et al.  Second Order Properties of Error Surfaces: Learning Time and Generalization , 1990, NIPS 1990.

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

[9]  K Kamijo,et al.  Integrated approach of an artificial neural network and numerical analysis to multiple equivalent current dipole source localization. , 2001, Frontiers of medical and biological engineering : the international journal of the Japan Society of Medical Electronics and Biological Engineering.

[10]  C. Nordling,et al.  Wavelengths and energy levels of the 4d95s-4d95p transition array of Xe IX , 1994 .

[11]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[12]  Qinyu Zhang,et al.  EEG source localization for two dipoles by neural networks , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[13]  Mingui Sun,et al.  The forward EEG solutions can be computed using artificial neural networks , 2000, IEEE Transactions on Biomedical Engineering.

[14]  S. Sato,et al.  Localization of implanted dipoles by magnetoencephalography , 1991, Neurology.

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

[16]  Andreas Ziehe,et al.  Artifact Reduction in Magnetoneurography Based on Time-Delayed Second Order Correlations , 1998 .

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

[18]  J Beatty,et al.  Magnetic localization of a dipolar current source implanted in a sphere and a human cranium. , 1986, Electroencephalography and clinical neurophysiology.

[19]  Barak A. Pearlmutter,et al.  Fast accurate MEG source localization using a multilayer perceptron trained with real brain noise. , 2002, Physics in medicine and biology.

[20]  S Kuriki,et al.  Localization accuracy of single current dipoles from tangential components of auditory evoked fields. , 2002, Physics in medicine and biology.

[21]  Barak A. Pearlmutter,et al.  An MEG Study of Response Latency and Variability in the Human Visual System During a Visual-Motor Integration Task , 1999, NIPS.

[22]  Gabriel Curio,et al.  Cardiac artifact subspace identification and elimination in cognitive MEG data using time-delayed decorrelation , 2002, IEEE Transactions on Biomedical Engineering.

[23]  Jerry Avorn.  Technology , 1929, Nature.

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

[25]  Michelle A. Espy,et al.  Performance of a novel squid-based superconducting imaging-surface magnetoencephalography system , 2002 .

[26]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[27]  Tsunehiro Takeda,et al.  Single-Trial Magnetoencephalographic Data Decomposition and Localization Based on Independent Component Analysis Approach , 2000 .

[28]  Rik Van de Walle,et al.  Comparison of performance of spherical and realistic head models in dipole localization from noisy EEG. , 2002, Medical engineering & physics.

[29]  Hirofumi Nagashino,et al.  Dipole source localization of MEG by BP neural networks , 2005, Brain Topography.

[30]  M. E. Spencer,et al.  A Study of Dipole Localization Accuracy for MEG and EEG using a Human Skull Phantom , 1998, NeuroImage.

[31]  Barak A. Pearlmutter,et al.  MEG source localization using an MLP with a distributed output representation , 2003, IEEE Transactions on Biomedical Engineering.

[32]  G. Nolte.  The magnetic lead field theorem in the quasi-static approximation and its use for magnetoencephalography forward calculation in realistic volume conductors. , 2003, Physics in medicine and biology.

[33]  J J Riera,et al.  Evaluation of inverse methods and head models for EEG source localization using a human skull phantom , 2001, Physics in medicine and biology.

[34]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[35]  Jan C. de Munck,et al.  The localization of spontaneous brain activity: an efficient way to analyze large data sets , 2001, IEEE Transactions on Biomedical Engineering.

[36]  G. Curio,et al.  Perturbation theory as a new analytical approach to the MEG forward problem for realistic volume conductor modeling of the head , 2001 .

[37]  S Makeig,et al.  Blind separation of auditory event-related brain responses into independent components. , 1997, Proceedings of the National Academy of Sciences of the United States of America.

[38]  Barak A. Pearlmutter,et al.  Independent Components of Magnetoencephalography: Localization , 2002, Neural Computation.

[39]  Andreas Ziehe,et al.  Independent component analysis of noninvasively recorded cortical magnetic DC-fields in humans , 2000, IEEE Transactions on Biomedical Engineering.

[40]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[41]  Barak A. Pearlmutter,et al.  Blind source separation of multichannel neuromagnetic responses , 2000, Neurocomputing.

[42]  R M Leahy,et al.  A sensor-weighted overlapping-sphere head model and exhaustive head model comparison for MEG. , 1999, Physics in medicine and biology.

[43]  R. Ilmoniemi,et al.  Magnetoencephalography-theory, instrumentation, and applications to noninvasive studies of the working human brain , 1993 .

[44]  Barak A. Pearlmutter,et al.  Fast robust MEG source localization using MLPs , 2002 .