MEG source localization using an MLP with a distributed output representation

We present a system that takes realistic magnetoencephalographic (MEG) signals and localizes a single dipole to reasonable accuracy in real time. At its heart is a multilayer perceptron (MLP) which takes the sensor measurements as inputs, uses one hidden layer, and generates as outputs the amplitudes of receptive fields holding a distributed representation of the dipole location. We trained this Soft-MLP on dipolar sources with real brain noise and converted the network's output into an explicit Cartesian coordinate representation of the dipole location using two different decoding strategies. The proposed Soft-MLPs are much more accurate than previous networks which output source locations in Cartesian coordinates. Hybrid Soft-MLP-start-LM systems, in which the Soft-MLP output initializes Levenberg-Marquardt, retained their accuracy of 0.28 cm with a decrease in computation time from 36 ms to 30 ms. We apply the Soft-MLP localizer to real MEG data separated by a blind source separation algorithm, and compare the Soft-NMP dipole locations to those of a conventional system.

[1]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

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

[3]  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.

[4]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

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

[6]  R Van Uitert,et al.  Finite Elenent EEG and MEG Simulations for Realistic Head Models: Quadratic vs. Linear Approximations , 2001 .

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

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

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

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

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[12]  Michelle A. Espy,et al.  Performance of a novel squid-based superconducting imaging-surface magnetoencephalography system , 2001 .

[13]  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.

[14]  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.