Mitotic HEp-2 Cells Recognition under Class Skew

  • Gennaro Percannella
  • Paolo Soda
  • Mario Vento
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6979)


Indirect immunofluorescence (IIF) is the recommended method to diagnose the presence of antinuclear autoantibodies in patient serum. A main step of the diagnostic procedure requires to detect mitotic cells in the well under examination. However, such cells rarely occur in comparison to other cells and, hence, traditional recognition algorithms fail in this task since they cannot cope with large differences between the number of samples in each class, resulting in a low predictive accuracy over the minority class. In this paper we present a system for mitotic cells recognition based on multiobjective optimisation, which is able to handle their low a priori probability. It chooses between the output of a classifier trained on the original skewed distribution and the output of a classifier trained according to a learning method addressing the course of imbalanced data. This choice is driven by a parameter whose value maximises, on a validation set, two objective functions, i.e. the global accuracy and the accuracies for each class. The approach has been evaluated on an annotated dataset of mitotic cells and successfully compared to five learning methods applying four different classification paradigms.


Support Vector Machine Multiobjective Optimisation Mitotic Cell Minority Class Class Imbalance 
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.


  1. 1.
    Kavanaugh, A., Tomar, R., et al.: Guidelines for clinical use of the antinuclear antibody test and tests for specific autoantibodies to nuclear antigens. American College of Pathologists, Archives of Pathology and Laboratory Medicine 124(1), 71–81 (2000)Google Scholar
  2. 2.
    Rigon, A., Soda, P., et al.: Indirect immunofluorescence in autoimmune diseases: Assessment of digital images for diagnostic purpose. Cytometry B (Clinical Cytometry) 72, 472–477 (2007)CrossRefGoogle Scholar
  3. 3.
    Bizzaro, N., Tozzoli, R., et al.: Variability between methods to determine ANA, anti-dsDNA and anti-ENA autoantibodies: a collaborative study with the biomedical industry. Journal of Immunological Methods 219, 99–107 (1998)CrossRefGoogle Scholar
  4. 4.
    Sack, U., Knoechner, S., et al.: Computer-assisted classification of HEp-2 immunofluorescence patterns in autoimmune diagnostics. Autoimmunity Reviews 2, 298–304 (2003)CrossRefGoogle Scholar
  5. 5.
    Hiemann, R., Hilger, N., et al.: Objective quality evaluation of fluorescence images to optimize automatic image acquisition. Cytometry Part A 69, 182–184 (2006)CrossRefGoogle Scholar
  6. 6.
    Soda, P., Rigon, A., et al.: Automatic acquisition of immunofluorescence images: Algorithms and evaluation. In: Computer Based Medical Systems, pp. 386–390. IEEE Computer Society, Los Alamitos (2006)Google Scholar
  7. 7.
    Huang, Y.L., Jao, Y.L., et al.: Adaptive automatic segmentation of HEp-2 cells in indirect immunofluorescence images. In: IEEE Int. Conf. on Sensor Networks, Ubiquitous and Trustworthy Computing, pp. 418–422 (2008)Google Scholar
  8. 8.
    Huang, Y.L., Chung, C.W., et al.: Outline detection for the HEp-2 cells in indirect immunofluorescence images using watershed segmentation. In: IEEE Int. Conf. on Sensor Networks, Ubiquitous and Trustworthy Computing, pp. 423–427 (2008)Google Scholar
  9. 9.
    Perner, P., Perner, H., Muller, B.: Mining knowledge for HEp-2 cell image classification. Journal Artificial Intelligence in Medicine 26, 161–173 (2002)CrossRefzbMATHGoogle Scholar
  10. 10.
    Soda, P., Iannello, G., Vento, M.: A multiple experts system for classifying fluorescence intensity in antinuclear autoantibodies analysis. Pattern Analysis & Applications 12(3), 215–226 (2009)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Hiemann, R., Büttner, T., et al.: Challenges of automated screening and differentiation of non-organ specific autoantibodies on HEp-2 cells. Autoimmunity Reviews 9(1), 17–22 (2009)CrossRefGoogle Scholar
  12. 12.
    Hiemann, R., Hilger, N., et al.: Automatic analysis of immunofluorescence patterns of HEp-2 cells. Annals of the New York Academy of Sciences 1109(1), 358–371 (2007)CrossRefGoogle Scholar
  13. 13.
    Soda, P., Iannello, G.: Aggregation of classifiers for staining pattern recognition in antinuclear autoantibodies analysis. IEEE Transactions on Information Technology in Biomedicine 13(3), 322–329 (2009)CrossRefGoogle Scholar
  14. 14.
    Foggia, P., Percannella, G., et al.: Early experiences in mitotic cells recognition on hep-2 slides. In: 23rd IEEE Int. Symp. on. Computer-Based Medical Systems, CBMS 2010, pp. 38–43 (2010)Google Scholar
  15. 15.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research 16(3), 321–357 (2002)zbMATHGoogle Scholar
  16. 16.
    Barandela, R., Sanchez, J.S., Garca, V., Rangel, E.: Strategies for learning in class imbalance problems. Pattern Recognition 36(3), 849–851 (2003)CrossRefGoogle Scholar
  17. 17.
    Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: One-sided selection. In: Machine Learning-International Workshop Then Conference, pp. 179–186. Morgan Kaufmann Publishers, Inc., San Francisco (1997)Google Scholar
  18. 18.
    Liu, X.Y., Wu, J., Zhou, Z.H.: Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 39(2), 539–550 (2009)CrossRefGoogle Scholar
  19. 19.
    Soda, P.: An experimental comparison of MES aggregation rules in case of imbalanced datasets. In: 22nd IEEE Int. Symp. on Computer-Based Medical Systems, 2009, pp. 1–6 (2009)Google Scholar
  20. 20.
    Soda, P.: A multi-objective optimisation approach for class-imbalance learning. Pattern Recognition (2010) (in press)Google Scholar
  21. 21.
    Woods, K., Kegelmeyer, W.P., Bowyer, K.: Combination of multiple classifiers using local accuracy estimates. IEEE Transactions on Pattern Analysis and Machine Intelligence 19, 405–410 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Gennaro Percannella
    • 1
  • Paolo Soda
    • 2
  • Mario Vento
    • 1
  1. 1.Dipartimento di Ingegneria dell’Informazione ed Ingegneria ElettricaUniversità di SalernoItaly
  2. 2.Facoltà di IngegneriaUniversità Campus Bio-Medico di RomaItaly

Personalised recommendations