Machine Vision and Applications

, Volume 24, Issue 7, pp 1405–1420 | Cite as

Breast cancer diagnosis from biopsy images with highly reliable random subspace classifier ensembles

  • Yungang ZhangEmail author
  • Bailing Zhang
  • Frans Coenen
  • Wenjin Lu
Special Issue Paper


Accurate and reliable classification of microscopic biopsy images is an important issue in computer assisted breast cancer diagnosis. In this paper, a new cascade Random Subspace ensembles scheme with reject options is proposed for microscopic biopsy image classification. The classification system is built as a serial fusion of two different Random Subspace classifier ensembles with rejection options to enhance the classification reliability. The first ensemble consists of a set of Support Vector Machine classifiers that converts the original \(K\)-class classification problem into a number of \(K\) 2-class problems. The second ensemble consists of a Multi-Layer Perceptron ensemble, that focuses on the rejected samples from the first ensemble. For both of the ensembles, the reject option is implemented by relating the consensus degree from majority voting to a confidence measure, and abstaining to classify ambiguous samples if the consensus degree is lower than some threshold. We also investigated the effectiveness of a feature description approach by combining Local Binary Pattern (LBP) texture analysis, statistics derived using the Gray Level Co-occurrence Matrix (GLCM) and the Curvelet Transform. While the LBP analysis efficiently describes local texture properties and the GLCM reflects global texture statistics, the Curvelet Transform is particularly appropriate for the representation of piece-wise smooth images with rich edge information. The combined feature description thus provides a comprehensive biopsy image characterization by taking advantages of their complementary strengths. Using a benchmark microscopic biopsy image dataset, obtained from the Israel Institute of Technology, a high classification accuracy of \(99.25 \%\) was obtained (with a rejection rate of \(1.94 \%\)) using the proposed system.


Breast cancer diagnosis Biopsy image Random subspace ensemble Reject option  Combined feature 


  1. 1.
    Breast Cancer Facts& Figures 2009–2010, American Cancer Society (2010)Google Scholar
  2. 2.
    Gaurav, A., Pradeep, P.V., Aggarwal, V., Yip, C.-H., Cheung, P.S.Y.: Spectrum of breast cancer in Asian women. World J. Surg. 31(5), 1031–1040 (2007)CrossRefGoogle Scholar
  3. 3.
    Linos, E., Spanos, D., Rosner, B.A., Linos, K., Hesketh, T., Qu, J.D., Gao, Y.-T., Zheng, Wei, Colditz, Graham A.: Effects of reproductive and demographic changes on breast cancer incidence in china: a modeling analysis. J. Natl. Cancer Inst. 100(19), 1352–1360 (2008)CrossRefGoogle Scholar
  4. 4.
    Arisio, R., Cuccorese, C., Accinelli, G., Mano, M.P., Bordon, R., Fessia, L.: Role of fine-needle aspiration biopsy in breast lesions: analysis of a series of 4,110 cases. Diagn. Cytopathol. 18(6), 462–467 (1998)CrossRefGoogle Scholar
  5. 5.
    Brook, A., El-Yaniv, R., Isler, E., Kimmel, R., Meir, R., Peleg, D.: Breast cancer diagnosis from biopsy images using generic features and SVMs. Tech. Rep. CS-2008-07, Technion-Israel Institute of Technology, Technion City, Haifa 32000, Isreal (2006)Google Scholar
  6. 6.
    Boucheron, L.E.: Object- and spatial-level quantitative analysis of multispectral histopathology images for detection and characterization of cancer. Ph.D. Thesis, University of California Santa Barbara, Santa Barbara, CA (2008)Google Scholar
  7. 7.
    Loukas, C.: A survey on histological image analysis-based assessment of three major biological factors influencing radiotherapy: proliferation, hypoxia and vascluature. Comput. Methods Programs Biomed. 74(3), 183–199 (2004)CrossRefGoogle Scholar
  8. 8.
    Orlov, N., Shamir, L., Macura, T., Johnston, J., Eckley, D.M., Goldberg, I.G.: Wnd-charm: multi-purpose image classification using compound image transforms. Pattern Recognit. Lett. 29(11), 1684–1693 (2008)CrossRefGoogle Scholar
  9. 9.
    Tabesh, A., Teverovskiy, M., Pang, H.-Y., Kumar, V.P., Verbel, D., Kotsianti, A., Saidi, O.: Multifeature prostate cancer diagnosis and gleason grading of histological images. IEEE Trans. Med. Imaging 26(10), 1366–1378 (2007)CrossRefGoogle Scholar
  10. 10.
    Qureshi, H., Sertel, O., Rajpoot, N., Wilson, R., Gurcan, M.: Adaptive discriminant wavelet package transform and local binary patterns for meningioma subtype classification. MICCAI 2008, 196–204 (2008)Google Scholar
  11. 11.
    Gurcan, Metin N., Boucheron, L.E., Can, A., Madabhushi, A., Rajpoot, N.M., Yener, B.: Histopathological image analysis: a review. IEEE Rev. Boimed. Eng. 2, 147–171 (2009)CrossRefGoogle Scholar
  12. 12.
    Yang, P., Yang, Y.H., Zhou, B.B., Zomaya, A.Y.: A review of ensemble methods in bioinformatics. Curr. Bioinforma. 5(4), 296–308 (2010)CrossRefGoogle Scholar
  13. 13.
    Freund, Y.: Boosting a weak learning algorithm by majority. Inf. Comput. 121(2), 256–285 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, New York (2004)CrossRefGoogle Scholar
  15. 15.
    Ho, T.K.: The random subspace method for constructing decision forests. IEEE Trans. PAMI 20, 832–844 (1998)CrossRefGoogle Scholar
  16. 16.
    Kuncheva, L.I., Rodriguez, J.J., Plumpton, C.O., Linden, D.E., Johnston, S.J.: Random subspace ensembles for FMRI classification. IEEE Trans. Med. Imaging. 29(2), 531–542 (2010)CrossRefGoogle Scholar
  17. 17.
    Bertoni, A., Folgieri, R., Valentini, G.: Biological and Artificial Intelligence Environments. Springer, Berlin (2008)Google Scholar
  18. 18.
    Pudil, P., Novovicova, J., Blaha, S., Kittler, J.: Multistage pattern recognition with reject option. In: Proceeding of the Eleventh IAPR International Conference on Pattern Recognition B, pp. 92–95 (1992)Google Scholar
  19. 19.
    Alpaydin, E., Kaynak, C.: Cascading Classifiers. Kybernetika, vol. 34, pp. 369–374Google Scholar
  20. 20.
    Kaynak, C.: Alpaydin, E.: Multistage cascading of multiple classifiers: one man’s noise is another man’s data. In: Proceedings of ICML, 2000, pp. 455–462 (2000)Google Scholar
  21. 21.
    Chow, C.K.: On optimum recognition error and reject tradeoff. IEEE Trans. Inf. Theory IT–16(1), 41–46 (1970)CrossRefGoogle Scholar
  22. 22.
    Pudil, P., Novovicova, J., Blaha, S., Kittler, J.: Multistage pattern recognition with reject option. In: Proceedings of 11th IAPR International Conference on Pattern Recognition, vol. 2, pp. 92–95 (1992)Google Scholar
  23. 23.
    Fumera, G., Roli, F.: Support vector machines with embedded reject option. In: International Workshop on Pattern Recognition with Support Vector Machines (SVM2002), pp. 68–82. Springer, Niagara Falls, Canada (2002)Google Scholar
  24. 24.
    Giusti, N., Masulli, F., Sperduti, A.: A theoretical and experimental analysis of a two-stage system for classification. IEEE Trans. Pattern Anal. Mach. Intell. 24, 893–904 (2002)CrossRefGoogle Scholar
  25. 25.
    Nadeem, MSA., Zucker, J.-D., Hanczar, B.: Accuracy-rejection curves (ARCs) for comparing classification methods with a reject option. In: Proceedings of the Third International Workshop on Machine Learning in Systems Biology, Ljubljana, Slovenia, pp. 5–6 (2009)Google Scholar
  26. 26.
    Hanczar, B., Dougherty, E.R.: Classification with reject option in gene expression data. Bioinformatics 24(17), 1889–1895 (2010)CrossRefGoogle Scholar
  27. 27.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (July 2002)Google Scholar
  28. 28.
    Guo, Z., Zhang, L., Zhang, D.: A completed modeling of local binary pattern operator for texture classification. IEEE Trans. Image Process. (2010) (accepted)Google Scholar
  29. 29.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 3(6), 610–621 (1973)CrossRefGoogle Scholar
  30. 30.
    Boland, M.V.: Quantitative description and automated classification of cellular protein localization patterns in fluorescence microscope images of mammalian cells. Ph.D. Thesis, Carnegie Mellon University, Pittsburgh (1999)Google Scholar
  31. 31.
    Clausi, D.A.: An analysis of co-occurence texture statistics as a function of grey level quantization. Can. J. Remote Sensing 28(1), 45–62 (2002)CrossRefGoogle Scholar
  32. 32.
    Soh, L.-K., Tsatsoulis, C.: Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sensing 37(2), 780–795 (1999)CrossRefGoogle Scholar
  33. 33.
    Donoho, D., Duncan, M.: Digital Curvelet Transform: Strategy. Implementation and Experiments. Stanford University, Stanford (1999)Google Scholar
  34. 34.
    Starck, J., Candes, E., Donoho, D.: The curvelet transform for image denoising. IEEE Trans. Image Process. 11, 670–684 (2002)Google Scholar
  35. 35.
    Candes, E., Donoho, D.: Curvelets: multiresolution representation, and scaling laws. In: Aldroubi, A., Laine, A.F., Unser, M.A. (eds.) Wavelet Applications in Signal and ImageProcessing VIII, Proceeding of the SPIE 4119 (2000)Google Scholar
  36. 36.
    Candes, E., Demanet, L., Donoho, D., Ying, L.: Fast discrete curvelet transforms. Multiscale Model. Simul. 5, 861–899 (2006) Google Scholar
  37. 37.
    Ma, J., Plonka, G.: The curvelet transform: a review of recent applications. IEEE Signal Process. Mag. 27(2), 118–133 (2010)CrossRefGoogle Scholar
  38. 38.
    Meselhy Eltoukhy, M., Faye, I., Belhaouari Samir, B.: Breast cancer diagnosis in digital mammogram using multiscale curvelet transform. Comput. Med. Imaging Graph. 34, 269–276 (2010)CrossRefGoogle Scholar
  39. 39.
    Zhang, B., Pham, T.D.: Phenotype recognition with combined features and random subspace classifier ensemble. BMC Bioinforma. 12, 128 (2010)CrossRefGoogle Scholar
  40. 40.
    Zhang, P., Bui, T.D., Suen, C.Y.: A novel cascade ensemble classifier system with a high recognition performance on handwritten digits. Pattern Recognit. 40, 3415–3429 (2007)CrossRefzbMATHGoogle Scholar
  41. 41.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Berlin (1995)CrossRefGoogle Scholar
  42. 42.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)Google Scholar
  43. 43.
    Kuncheva, L.I., Skurichina, M., Duin, R.P.: An experimental study on diversity for bagging and boosting with linear classifiers. Inf. Fusion 3(4), 245–258 (2002)CrossRefGoogle Scholar
  44. 44.
    Tax, D.M.J., Duin, R.P.W.: Growing a multi-class classifier with a reject option. Pattern Recognit. Lett. 29(10), 1565–1570 (2008)CrossRefGoogle Scholar
  45. 45.
    Tax, D.M.J., Duin, R.P.W.: Support vector domain description. Pattern Recognit. Lett. 20(11–13), 1191–1199 (1999)CrossRefGoogle Scholar
  46. 46.
    Lam, L., Suen, C.Y.: Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE Trans. Syst. Man Cybern. Part A Syst. Human 27, 553–568 (1997)CrossRefGoogle Scholar
  47. 47.
    Giusti, N., Masuli, F., Sperduti, A.: Theoretical and experimental analysis of a two-stage system for classification. IEEE Trans. PAMI 24(7), 893–904 (2002)CrossRefGoogle Scholar
  48. 48.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)zbMATHGoogle Scholar
  49. 49.
    Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)zbMATHGoogle Scholar
  50. 50.
    Breiman, L.: Bagging predictors. Mach. Learn. 26(2), 123–140 (1996)Google Scholar
  51. 51.
    Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Proceeding of 13th International Conference on Machine Learning, San Francisco, CA, USA. pp. 148–156 (1996)Google Scholar
  52. 52.
    Breiman, L.: Random For. Machine Learning 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yungang Zhang
    • 1
    • 3
    Email author
  • Bailing Zhang
    • 2
  • Frans Coenen
    • 1
  • Wenjin Lu
    • 2
  1. 1.Department of Computer ScienceUniversity of LiverpoolLiverpoolUK
  2. 2.Department of Computer ScienceXi’an JiaoTong-Liverpool UniversitySuzhouPeople’s Republic of China
  3. 3.School of Information ScienceYunnan Normal UniversityKunmingPeople’s Republic of China

Personalised recommendations