Summary
The purpose of this study was to examine the usefulness of BP neural networks for source localization of MEG. Since the performance of this method does not depend on the complexity of brain parameters and source models, a homogeneous brain model and a single current dipole source are assumed for convenience. Localization accuracy was examined in relation to the configuration and scale of the network. As a result, average error for position and moment estimations was within 2%, while the maximum error was about 5%. It was therefore concluded that the neural network method was useful for MEG source localization, though some improvements are still necessary.
Similar content being viewed by others
References
Abeyratne, U.R., Kinouchi, Y., Oki, H., Okada, J., Shichijo, F. and Matsumoto, K. Artificial Neural Networks for Source Localization in the Human Brain. Brain Topography, 1991, 4: 3–21.
Abeyratne, U.R., Kinouchi, Y., Soga, T., Okada, J., Shichijo, F. and Matsumoto, K. Artificial Neural Networks for Multiple Dipole Localization: A Feasibility Study. In: Abstracts of the Second International Congress on Brain Electromagnetic Topography, Toronto, Canada, 1991: 33.
Hosaka, H. On the Basic Study of Magnetic Detection of Electrical Activity in the Heart. Japanese Journal of Medical and Biological Engineering, 1976, 14: 34–40.
Rumelhart, D.E., Hinton, G.E. and Williams, R.J. Learning Internal Representation by Error Propagation. In: D.E. Rumelhart, J.L. McClelland, and the PDP Research Group (Eds.), Parallel Distributed Processing. MIT Press, Cambridge, 1986: 318–362.
Ueno, S. and Iramina, K. Modeling and Source Localization of MEG Activities. Brain Topography, 1990, 3: 151–165.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kinouchi, Y., Ohara, G., Nagashino, H. et al. Dipole source localization of MEG by BP neural networks. Brain Topogr 8, 317–321 (1996). https://doi.org/10.1007/BF01184791
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01184791