Improving Pit–Pattern Classification of Endoscopy Images by a Combination of Experts

  • Michael Häfner
  • Alfred Gangl
  • Roland Kwitt
  • Andreas Uhl
  • Andreas Vécsei
  • Friedrich Wrba
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5761)


The diagnosis of colorectal cancer is usually supported by a staging system, such as the Duke or TNM system. In this work we discuss computer–aided pit–pattern classification of surface structures observed during high–magnification colonoscopy in order to support dignity assessment of colonic polyps. This is considered a quite promising approach because it allows in vivo staging of colorectal lesions. Since recent research work has shown that the characteristic surface structures of the colon mucosa exhibit texture characteristics, we employ a set of texture image features in the wavelet-domain and propose a novel classifier combination approach which is similar to a combination of experts. The experimental results of our work show superior classification performance compared to previous approaches on both a two-class (non-neoplastic vs. neoplastic) and a more complicated six-class (pit–pattern) classification problem.


Feature Subset Endoscopy Image Colorectal Lesion Feature Extraction Approach Predict Class Label 
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.
    Kudo, S.: Colorectal Tumours and Pit Pattern. Journal of Clinical Pathology 47(10), 880–885 (1994)CrossRefGoogle Scholar
  2. 2.
    Hurlstone, D.: High-Resolution Magnification Chromoendoscopy: Common Problems Encountered in Pit-Pattern Interpretation and Correct Classification of Flat Colorectal Lesions. American Journal of Gastroenterology 97(4), 1069–1070 (2002)Google Scholar
  3. 3.
    Kato, S., Fujii, T., Koba, I., Sano, Y., Fu, K.I., Parra-Blanco, A., Tajiri, H., Yoshida, S., Rembacken, B.: Assessment of Colorectal Lesions Using Magnifying Colonoscopy and Mucosal Dye Spraying: Can Significant Lesions Be Distinguished? Endoscopy 33(3), 306–311 (2001)CrossRefGoogle Scholar
  4. 4.
    Kato, S., Fu, K., Sano, Y., Fujii, T., Saito, Y., Matsuda, T., Koba, I., Yoshida, S., Fujimori, T.: Magnifying Colonoscopy as a Non-Biopsy Technique for Differential Diagnosis of Non-Neoplastic and Neoplastic Lesions. World of Gastroenterology 12(9), 1416–1420 (2006)CrossRefGoogle Scholar
  5. 5.
    Hurlstone, D., Cross, S., Adam, I., Shorthouse, A., Brown, S., Sanders, D., Lobo, A.: Efficiacy of High Magnification Chromoscopic Colonoscopy for the Diagnosis of Neoplasia in Flat and Depressed Lesions of the Colorectum: a Prospective Analysis. Gut 53, 284–290 (2004)CrossRefGoogle Scholar
  6. 6.
    Fu, K.: Chromoendoscopy using Indigo Carmine Dye Spraying with Magnifying Observation is the most Reliable Method for Differential Diagnosis between Non-Neoplastic and Neoplastic Colorectal Lesions. Endoscopy 36(12), 1089–1093 (2004)CrossRefGoogle Scholar
  7. 7.
    Meining, A.: Inter- and Intra-Observer Variability of Magnification Chromoendoscopy for Detecting Specialized Intestinal Metaplasia at the Gastroesophageal Junction. Endoscopy 36(2), 160–164 (2004)CrossRefGoogle Scholar
  8. 8.
    Kwitt, R., Uhl, A.: Modeling the marginal distributions of complex wavelet coefficient magnitudes for the classification of Zoom-Endoscopy images. In: Proceedings of the IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2007), Rio de Janeiro, Brazil, pp. 1–8 (2007)Google Scholar
  9. 9.
    Kwitt, R., Uhl, A.: Color Eigen-Subband Features for Endoscopy Image Classification. In: Proceedings of the 33rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008), Las Vegas, Nevada, USA, pp. 589–592 (2008)Google Scholar
  10. 10.
    Van de Wouwer, G., Livens, S., Scheunders, P., Van Dyck, D.: Color Texture Classification by Wavelet Energy Correlation Signatures. In: Proceedings of the 9th International Conference on Image Analysis and Processing (ICIAP 1997), pp. 327–334. Springer, Heidelberg (1997)Google Scholar
  11. 11.
    Park, S.-H., Fürnkranz, J.: Efficient pairwise classification. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds.) ECML 2007. LNCS, vol. 4701, pp. 658–665. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Fukunaga, K.: Introduction to Statistical Pattern Recognition. Morgan Kaufmann, San Francisco (1990)zbMATHGoogle Scholar
  13. 13.
    Hansen, L., Salamon, P.: Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(10), 993–1001 (1990)CrossRefGoogle Scholar
  14. 14.
    Breiman, L.: Bagging predictors. Machine Learning 24(2), 123–140 (1996)zbMATHGoogle Scholar
  15. 15.
    Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: Proceedings of the 13th International Conference on Machine Learning (ICML 1996), Bari, Italy, pp. 148–156 (1996)Google Scholar
  16. 16.
    Bay, S.: Nearest Neighbor Classification from Multiple Feature Subsets. Intelligent Data Analysis 3(3), 191–209 (1999)CrossRefGoogle Scholar
  17. 17.
    Cutzu, F.: How to do multi-way classification with two-way classifiers. In: 3rd Joint International Conference on Artificial Neural Networks and Neural Information Processing, Istanbul, Turkey, pp. 375–384 (2003)Google Scholar
  18. 18.
    Dietterich, T.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10(7), 1895–1923 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Michael Häfner
    • 1
  • Alfred Gangl
    • 1
  • Roland Kwitt
    • 2
  • Andreas Uhl
    • 2
  • Andreas Vécsei
    • 4
  • Friedrich Wrba
    • 3
  1. 1.Dept. of Gastroenterology & HepatologyMedical University of ViennaAustria
  2. 2.Dept. of Computer ScienceUniversity of SalzburgAustria
  3. 3.Dept. of Clinical PathologyMedical University of ViennaAustria
  4. 4.St. Anna Children’s HospitalViennaAustria

Personalised recommendations