Magnetocardiogram Topography with Automatic Artifact Correction using Principal Component Analysis and Artificial Neural Network

  • Ahn C.B. (VIA Multimedia Center, Kwangwoon University) ;
  • Kim T.H. (VIA Multimedia Center, Kwangwoon University) ;
  • Park H.C. (VIA Multimedia Center, Kwangwoon University) ;
  • Oh S.J. (VIA Multimedia Center, Kwangwoon University)
  • Published : 2006.04.01


Magnetocardiogram (MCG) topography is a useful diagnostic technique that employs multi-channel magnetocardiograms. Measurement of artifact-free MCG signals is essenctial to obtain MCG topography or map for a diagnosis of human heart. Principal component analysis (PCA) combined with an artificial neural network (ANN) is proposed to remove a pulse-type artifact in the MCG signals. The algorithm is composed of a PCA module which decomposes the obtained signal into its principal components, followed by an ANN module for the classification of the components automatically. In the experiments with volunteer subjects, 97% of the decisions that were made by the ANN were identical to those by the human experts. Using the proposed technique, the MCG topography was successfully obtained without the artifact.


  1. C.B. Ahn, T.H. Kim, S.J Oh, and H.J Park, 'Automatic Artifact Correction Using Principal Component Analysis and Neural Network in Magnetocardiography Signal', Proc. ITC-CSCC 2005, pp.961-962, 2005
  2. D.H. Lee and C.B. Ahn, 'Automatic Artifact Removal Using a Neural Network in MCG Signal', Proc. 14th IntI. Conf. Biomagnetism (Biomag2004), pp.163-164, 2004
  3. W. Andra and H. Nowak ed, Magnetism in Medicine, Wiley-VCH, 1998
  4. J. Wikswo, Jr., 'SQUID Magnetometers for Biomagnetism and Nondestructive Testing: Important Questions and Initial Answers', IEEE Trans. Appl. Supercon., Vol. 5, pp.74-119, 1995
  5. J. Clarke, 'Prinicples andApplications of SQUIDs', Proc. IEEE, Vol.77, pp.1208-1223, 1989
  6. H.N. Lee, K.W. Kim, S.Y. Lee, M.H. Cho, Y. Huh, 'Magnetic Noise Reduction in MCG Using Spatial Filters', J Biomed. Eng. Res., VoI.24, pp.287-292, 2003
  7. T. Kobayashi and S. Kuriki, 'Principal Component Elimination Method for the Improvement of S/N in Evoked Neuromagnetic Field Measurements', IEEE Trans. Biomed. Engin., Vol. 46, pp. 951-958, 1999
  8. C.B. Ahn, S.H. Lee, and T.Y. Lee, 'EEG and Artifact Classification using Neural Network', Proc. 18th Annual Conference of the IEEE Engineering in Medicine and Biology Society, p.306, Oct.31-Nov.3, Amsterdam, Netherlands, 1996