Neural Computing & Applications

, Volume 2, Issue 4, pp 209–215 | Cite as

A dental application of neural network computing: Classification of complex electrical impedance measurements to aid root canal treatment

  • Malcolm Levinkind


Electrical impedance measurements provide an alternative diagnostic technique to the use of radiographs for aiding dental root canal treatment. Analysis of impedance data was based on Complex NonLinear Least Squares (CNLS) regression with electrical circuits as models. Different equivalent circuits were required to model the data at various depths within root canals. Therefore, it was not valid to compare directly the parameter values obtained for the same electrical components when different circuits were used. This problem was solved with a neural computing approach based on supervised training of the backpropagation algorithm to classify the data. Two strategies were investigated. The first produced a network output which indicated the electrode depth within the canal. The second approach employed the neural network as a preprocessor to establish which equivalent circuit was appropriate for the CNLS. Tests were also carried out to determine the minimum number of input nodes required by a neural network for this dental application.


Neural network computing Complex electrical impedance Diagnosis Dental root canal length 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McDonald NJ. The electronic determination of working length. Dental Clinics of North America 1992; 36: 239–307Google Scholar
  2. 2.
    Levinkind M, Assavanop P, Ahlberg K. Root canal measurement by varied frequency of applied electrical signal. J Dent Res 1993; 72: 742, Abs. 443Google Scholar
  3. 3.
    Levinkind M, VanderNoot TJ, Elliott JC. Electrochemical impedance characterization of human and bovine enamel. J Dent Res 1990; 69: 1806–1811Google Scholar
  4. 4.
    VanderNoot T, Levinkind M. Ac impedance characteristics of human enamel and dentine. J Electroanal Chem 1991, 300: 191–198CrossRefGoogle Scholar
  5. 5.
    Levinkind M, VanderNoot TJ, Elliott JC. Evaluation of smear layers on serial sections of human dentin by means of electochemical impedance measurements. J Dent Res 1992; 71: 426–433Google Scholar
  6. 6.
    Levinkind M. Characterization of the electrical resistivity of serial sections of human dentine by means of a.c. impedance measurements. Int Endodontic J 1993; 26: 22–23Google Scholar
  7. 7.
    Levinkind M. Impedance spectroscopy of human enamel and dentine relating to their physical structure and equivalent circuits. PhD Thesis 1992, University of LondonGoogle Scholar
  8. 8.
    Mumford JM. Resistivity of human dentine. Archs Oral Biol 1965; 10: 957–968CrossRefGoogle Scholar
  9. 9.
    Macdonald JR. Chapter 3, Section 3.2, Data analysis. In: Macdonald JR (ed.). Impedance Spectroscopy, Emphasising Solid Materials and Systems, Chichester: Wiley-Interscience, 173–190, 1987Google Scholar
  10. 10.
    McClelland JL, Rumelhart DE. Parallel Distributed Processing, Volume 1. Cambridge, MA, MIT Bradford Press, 1986Google Scholar

Copyright information

© Springer-Verlag London Limited 1994

Authors and Affiliations

  • Malcolm Levinkind
    • 1
  1. 1.Department of Child Dental HealthThe London Hospital Medical CollegeLondonUK

Personalised recommendations