Article

MEG source localization using an MLP with a distributed output representation

Biol. & Quantum Phys. Group, Los Alamos Nat. Lab., NM, USA
IEEE Transactions on Biomedical Engineering (Impact Factor: 2.23). 07/2003; DOI: 10.1109/TBME.2003.812154
Source: IEEE Xplore

ABSTRACT 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.

Download full-text

Full-text

Available from: Barak A. Pearlmutter, Jun 21, 2013
0 Followers
 · 
134 Views
  • Source
    • "Recently, [Kamijo et al., 2001] and [Jun et al., 2002] studied hybrid approaches to EEG/MEG dipole source localization, in which trained MLPs are used as initializers for iterative methods. In addition, [Jun et al., 2003] proposed an MLPbased MEG dipole source localizer that uses a distributed output representation in the MLP structure, which is expected to be more easily extensible to the multiple dipole case. Interestingly, all work to date is trained with a fixed head model. "
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Human Brain Mapping 01/2005; 24(1):21-34. DOI:10.1002/hbm.20068 · 6.92 Impact Factor
  • Source
    • "Hoey et al. (2000) took EEG measurements for both spherical and realistic head models and trained MLPs on randomly generated noise-free datasets. Integrated approaches to the EEG/MEG dipole source localization, in which the trained MLPs are used as initializers for iterative methods, have also been studied (Jun et al., 2002) along with distributed output representations (Jun et al., 2003). Interestingly, all work to date trained with a fixed head model. "
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
  • Source
Show more