Evolving Neural Networks for the Classification of Malignancy Associated Changes

  • Jennifer Hallinan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3578)


Malignancy Associated Changes are subtle changes to the nuclear texture of visually normal cells in the vicinity of a cancerous or precancerous lesion. We describe a classifier for the detection of MACs in digital images of cervical cells using artificial neural networks evolved in conjunction with an image texture feature subset. ROC curve analysis is used to compare the classification accuracy of the evolved classifier with that of standard linear discriminant analysis over the full range of classification thresholds as well as at selected optimal operating points. The nonlinear classifier does not significantly outperform the linear one, but it generalizes more readily to unseen data, and its stochastic nature provides insights into the information content of the data.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Grimm, D.: Disease backs cancer origin theory. Science 5695, 389 (2004)CrossRefGoogle Scholar
  2. 2.
    Gruner, O.C.: Study of the changes met with the leukocytes in certain cases of malignant disease. British Journal of Surgery 3, 506–522 (1916)CrossRefGoogle Scholar
  3. 3.
    Nieburgs, H.E., Zak, R.G., Allen, D.C., Reisman, H., Clardy, T.: Systemic cellular changes in material from human and animal tissues in the presence of tumours. In: Transactions of the 7th Annual Meeting of the International Society for Cytology, pp. 137–144 (1959)Google Scholar
  4. 4.
    Bibbo, M., Bartels, P.H., Sychra, J.J., Weid, G.L.: Chromatin appearance in intermediate cells from patients with uterine cancer. Acta Cytologica 25, 23–28 (1981)Google Scholar
  5. 5.
    Susnik, B., Worth, A., Le Riche, J., Palcic, B.: Malignancy-associated changes in the breast: changes in chromatin distribution in epithelial cells in normal-appearing tissue adjacent to carcinoma. Analytical and Quantitative Cytology and Histology 17, 62–68 (1995)Google Scholar
  6. 6.
    Palcic, B., MacAulay, C.: Malignancy associated changes: Can they be employed clinically? In: Wied, G.L., Bartels, P.H., Rosenthal, D.L., Schenk, U. (eds.) Compendium on the Computerized Cytology and Histology Laboratory. Tutorials of Cytology, Chicago (1994)Google Scholar
  7. 7.
    Garner, D., Harrison, A., MacAulay, C., Palcic, B.: Cyto-Savant and its use in automated screening of cervical smears. In: Wied, G.L., Bartels, P.H., Rosenthal, D.L., Schenck, U. (eds.) Compendium on the Computerized Cytology and Histology Laboratory, Tutorials of Cytology (1994)Google Scholar
  8. 8.
    Hallinan, J.: Detection of Malignancy Associated Changes in cervical cells using statistical and evolutionary computation techniques. Unpublished PhD Thesis, The University of Queensland (2000)Google Scholar
  9. 9.
    Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1996)Google Scholar
  10. 10.
    van Erkel, A.R., Pattynama, P.M.: Receiver operating characteristsic (ROC) analysis: Basic principles and applications in radiology. European Journal of Radiology 27, 88–94 (1998)CrossRefGoogle Scholar
  11. 11.
    Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143, 29–36 (1982)Google Scholar
  12. 12.
    Bradley, A.P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition 30, 1145–1159 (1997)CrossRefGoogle Scholar
  13. 13.
    Palcic, B., Susnik, B., Garner, D., Olivotto, I.: Quantitative evaluation of malignant potential of early breast cancer using high resolution image cytometry. Journal of Cellular Biochemistry Suppl. 17G, 107–113 (1993)CrossRefGoogle Scholar
  14. 14.
    Payne, P.W., Sebo, T.J., Doudkine, A., Garner, D., MacAulay, C., Lam, S., LeRiche, J.C., Palcic, B.: Sputum screening by quantitative microscopy: A reexamination of a portion of the National Cancer Institute Cooperative early lung study. Mayo Clinic Proceedings 72, 697–704 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Jennifer Hallinan
    • 1
  1. 1.Institute for Molecular Bioscience and School of ITEEThe University of QueenslandBrisbaneAustralia

Personalised recommendations