Using an Artificial Neural Network to Determine Electrical Properties of Epithelia

  • Thomas Schmid
  • Dorothee Günzel
  • Martin Bogdan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6352)


The present study introduces a new approach for modeling electrical properties of epithelia. Artificial neural networks (ANNs) are used to estimate key parameters that otherwise can only be measured directly by applying complex and time-consuming laboratory methods. Assuming an electrical model equivalent to an epithelial layer, an ANN can be trained to learn the relation between these parameters and experimentally obtained impedance spectra. We demonstrate that even with a naive ANN our approach reduces the error rate of parameter estimation to less than 20 per cent. Successful test runs provide a proof of concept.


Electrical Model Nyquist Diagram Transcellular Pathway Alternate Current Frequency High Alternate Current Frequency 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Krug, S.M., Fromm, M., Günzel, D.: Two-path Impedance Spectroscopy for Measuring Paracellular and Transcellular Epithelial Resistance. Biophys. J. 97(8), 2202–2211 (2009)CrossRefGoogle Scholar
  2. 2.
    Bertrand, C.A., et al.: System for Dynamic Measurements of Membrane Capacitance in Intact Epithelial Monolayers. Biophys. J. 75(6), 2743–2756 (1998)CrossRefGoogle Scholar
  3. 3.
    Gitter, A.H., Fromm, M., Schulzke, J.D.: Impedance Analysis for the Determination of Epithelial and Subepithelial Resistance in Intestinal Tissues. J. Biochem. Biophys. Methods 37(1-2), 35–46 (1998)CrossRefGoogle Scholar
  4. 4.
    Clausen, C., Lewis, S.A., Diamond, J.M.: Impedance Analysis of a Tight Epithelium Using a Distributed Resistance Model. Biophys. J. 26(2), 291–317 (1979)CrossRefGoogle Scholar
  5. 5.
    Mohraz, K., Arras, M.K.: FORWISS Artificial Neural Network Simulation Toolbox. Bavarian Reserach Center for Knowledge-Based Systems (1996)Google Scholar
  6. 6.
    Mohraz, K., Protzel, P.: FlexNet - A Flexible Neural Network Construction Algorithm. In: 4th European Symposium on Artificial Neural Networks, pp. 111–116 (1996)Google Scholar
  7. 7.
    Kavzoglu, T., Mather, P.M.: The Role of Feature Selection in Artificial Neural Network Applications. Int. J. Remote Sens. 23(15), 2919–2937 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Thomas Schmid
    • 1
  • Dorothee Günzel
    • 2
  • Martin Bogdan
    • 1
  1. 1.Dept. of Computer Engineering, Faculty of Mathematics and InformaticsUniversity of LeipzigLeipzigGermany
  2. 2.Institute of Clinical PhysiologyCharitéBerlinGermany

Personalised recommendations