Automatic Morphological Classification of Lung Cancer Subtypes with Boosting Algorithms for Optimizing Therapy

  • Ching-Wei Wang
  • Cheng-Ping Yu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)


Patient-targeted therapies have recently been highlighted as important. An important development in the treatment of metastatic non-small cell lung cancer (NSCLC) has been the tailoring of therapy on the basis of histology. A pathology diagnosis of “non-specified NSCLC” is no longer routinely acceptable; an effective approach for classification of adenocarcinoma (AC) and squamous carcinoma (SC) histotypes is needed for optimizing therapy. In this study, we present a robust and objective automatic classification system for real time classification of AC and SC based on morphological tissue pattern of H&E images alone to assist medical experts in diagnosis of lung cancer. Various original and extended Densitometric and Haralick’s texture features are used to extract image features, and a Boosting algorithm is utilized to train the classifier, together with alternative decision tree as the base learner. For evaluation, 369 tissue samples were collected in tissue microarray format, including 97 adenocarcinoma and 272 squamous carcinoma samples. Using 10-fold cross validation, the technique achieved high accuracy of 92.41%, and we also found that the two Boosting algorithms (cw-Boost and AdaBoost.M1) perform consistently well in comparison with other popularly adopted machine learning methods, including support vector machine, neural network, single decision tree and alternative decision tree. This approach offers a robust, objective and rapid procedure for optimized patient-targeted therapies.


morphological classification computer vision adenocarcinoma squamous carcinoma boosting tissue microarray 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Argiris, A., Gadgeel, S.M., Dacic, S.: Subdividing nsclc: Reflections on the past, present, and future of lung cancer therap. Oncology 23, 1–4 (2009)Google Scholar
  2. 2.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Inc., New York (1995)zbMATHGoogle Scholar
  3. 3.
    Chapman, J., Miller, N., Lickley, H., Qian, J., Christens-Barry, W., Fu, Y., Yuan, Y., Axelrod, D.: Ductal carcinoma in situ of the breast (dcis) with heterogeneity of nuclear grade: prognostic effects of quantitative nuclear assessment. BMC Cancer 7(1), 174 (2007)CrossRefGoogle Scholar
  4. 4.
    Dubey, S., Powell, C.A.: Update in lung cancer 2008. Am. J. Respir. Crit. Care Med. 179(10), 860–868 (2009)CrossRefGoogle Scholar
  5. 5.
    Freund, Y., Mason, L.: The alternating decision tree learning algorithm. In: Proc. 16th International Conf. on Machine Learning, pp. 124–133. Morgan Kaufmann, San Francisco (1999)Google Scholar
  6. 6.
    Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: In Proceedings of the Thirteenth International Conference on Machine Learning, pp. 148–156 (1996)Google Scholar
  7. 7.
    Grilley-Olson, J.E., Hayes, D.N., Qaqish, B.F., Moore, D.T., Socinski, M.A., Yin, X., Leslie Wilkerson, K.O., Travis, W.D., Funkhouser, W.K., et al.: Validation of inter-observer agreement in lung cancer assessment. Journal of Clinical Oncology 27, 15 (2009)CrossRefGoogle Scholar
  8. 8.
    Haralick, R.M., Shanmugam, K., Dinstein: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics 3(6), 610–621 (1973)CrossRefGoogle Scholar
  9. 9.
    Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K.: Improvements to platt’s smo algorithm for svm classifier design. Neural Computation 13(3), 637–649 (2001)CrossRefzbMATHGoogle Scholar
  10. 10.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI, pp. 1137–1145 (1995)Google Scholar
  11. 11.
    Otsu, N.: A threshold selection method from gray level histograms. IEEE Trans. Systems, Man and Cybernetics 9, 62–66 (1979); minimize inter class varianceCrossRefGoogle Scholar
  12. 12.
    Quinlan, R.J.: C4.5: Programs for Machine Learning. Morgan Kaufmann Series in Machine Learning. Morgan Kaufmann, San Francisco (1993)Google Scholar
  13. 13.
    Sandler, A., Gray, R., Perry, M.C., Brahmer, J., Schiller, J.H., Dowlati, A., Lilenbaum, R., Johnson, D.H.: Paclitaxel-carboplatin alone or with bevacizumab for non-small-cell lung cancer. N. Engl. J. Med. 355(24), 2542–2550 (2006)CrossRefGoogle Scholar
  14. 14.
    Selvaggi, G.: Histologic subtype in nsclc: Does it matter? Oncology 23, 1–11 (2009)Google Scholar
  15. 15.
    American Cancer Society, (accessed June 9, 2009)
  16. 16.
    Ullmann, R., Morbini, P., Halbwedl, I., Bongiovanni, M., Gogg-Kammerer, M., Papotti, M., Gabor, S., Renner, H., Popper, H.H.: Protein expression profiles in adenocarcinomas and squamous cell carcinomas of the lung generated using tissue microarrays. J. Pathol. 203(3), 798–807 (2004)CrossRefGoogle Scholar
  17. 17.
    Wang, C.-W., Hunter, A.: A low variance error boosting algorithm. Applied Intelligence (2009)Google Scholar
  18. 18.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann Series in Data Management Systems. Morgan Kaufmann, San Francisco (2005)zbMATHGoogle Scholar
  19. 19.
    Zapotoczny, P., Zielinska, M., Nita, Z.: Application of image analysis for the varietal classification of barley: Morphological features. Journal of Cereal Science 48(1), 104–110 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ching-Wei Wang
    • 1
  • Cheng-Ping Yu
    • 2
  1. 1.Graduate Institute of Biomedical EngineeringNational Taiwan University of Science and TechnologyTaiwan
  2. 2.Department of PathologyTri-Service General HospitalTaiwan

Personalised recommendations