Abstract
This paper proposes an automatic classification system for the use in prostate cancer diagnosis. The system aims to detect and classify prostatic tissue textures captured from microscopic samples taken from needle biopsies. Biopsies are usually analyzed by a trained pathologist with different grades of malignancy typically corresponding to different structural patterns as well as apparent textures. In the context of prostate cancer diagnosis, four major groups have to be accurately recognized: stroma, benign prostatic hyperplasia, prostatic intraepithelial neoplasia, and prostatic carcinoma. Recently, multispectral imagery has been proposed as a new image acquisition modality which unlike conventional RGB-based light microscopy allows the acquisition of a large number of spectral bands within the visible spectrum, resulting in a large feature vector size. Many features in the initial feature set are irrelevant to the classification task and are correlated with each other, resulting in an increase in the computational complexity and a reduction in the recognition rate. In this paper, a Round-Robin (RR) sequential forward selection RR-SFS is used to address these problems. RR is a technique for handling multi-class problems with binary classifiers by training one classifier for each pair of classes. The experimental results demonstrate this finding when compared with classical method based on the multiclass SFS and other ensemble methods such as bagging/boosting with decision tree (C4.5) classifier where it is shown that RR-SFS method achieves the best results with a classification accuracy of 99.9%.
Similar content being viewed by others
References
Stewart, B.W., Kleihues, P.: World Cancer Report World Health Organization, International Agency for Research on Cancer (2003)
Kronz J.D., Westra W.H., Epstein J.I.: Mandatory second opinion surgical pathology at a Large Referral Hospital. Cancer 86(11), 2426–2435 (1999)
Bartels P.H. et al.: Nuclear chromatin texture in prostatic lesions: IPIN and adenocarcinoma. Anal. Quant. Cytol. Histol. 20(15), 389–396 (1998)
Clark T.D., Askin F.B., Bagnell C.R.: Nuclear roundness factor: a quantitative approach to grading in prostate carcinoma. Reliability of needle biopsy tissue, and the effect of tumor stage on usefulness. Prostate 10(3), 199–206 (1987)
Gleason, D.F., Tannenbaum, M. (eds.): The veteran’s administration cooperative urologic research group: histologic grading and clinical staging of prostatic carcinoma. In: Urologic Pathology: The Prostate, pp. 171–198, Lea Febiger, Philadephia (1977)
O’Dowd G.J., Veltri R.W., Miller M.C., Strum S.B.: The Gleason score: a significant biologic manifestation of prostate cancer aggressiveness on biopsy. Prostate Cancer Res. Inst. PCR Insights 4(1), 1–5 (2001)
Tabesh A., Kumar V., Pang H., Verbel D., Kotsianti A., Teverovskiy M., Saidi O.: Automated prostate cancer diagnosis and Gleason grading of tissue microarrays. Proc. SPIE Med. Imaging 5747, 58–70 (2005)
Huang P.W., Lee C.H.: Automatic classification for pathological prostate images based on fractal analysis. IEEE Trans. Med. Imaging 28(7), 1037–1050 (2009)
Liu, Y., Zahoa, T., Zhang, J.: Learning multispectral texture features for cervical cancer detection. In: Proceedings of IEEE International Symposium on Biomedical Imaging, pp. 169–172, Washington, DC (2002)
Barshack I., Kopolovic J., Malik Z., Rothmann C.: Spectral morphometric characterization of breast carcinoma cells. Br. J. Cancer 79(9–10), 1613–1619 (1999)
Larsh P., Cheriboga L., Yee H., Diem M.: Infrared spectroscopy of humans cells and tissue: detection of disease. Technol. Cancer Res. Treat. 1(1), 1–7 (2002)
Boucheron L., Bi Z., Harvey N., Manjunath B., Rimm D.: Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery. BMC Cell Biol. 8(Suppl 1), S8 (2007)
Masood K., Rajpoot N.: Colon biopsy classification. Ann. BMVA 2008(4), 1–16 (2008)
Roula, M.A., Diamond, J., Bouridane, A., Miller, P., Amira, A.: A multispectral computer vision system for automatic grading of prostatic neoplasia. In: Proceedings of IEEE International Symposium on Biomedical lmaging, pp. 193–196 (2002)
Roula, M.A., Bouridane, A., Miller, P.: A quadratic classifier based on multispectral texture features for prostate cancer diagnosis. In: Proceedings of the Seventh International Symposium on Signal Processing Applications, pp. 37–40, Paris, France (2003)
Jain A.K., Duin R.P.W., Mao J.: Statistical pattern recognition: a review. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 4–37 (2000)
Bouatmane S., Nekhoul B., Bouridane A., Tanougast C.: Classification of prostatic tissues using feature selection methods. IFMBE Proc. 16, 843–846 (2007)
Furnkranz J.: Round Robin classification. J. Mach. Learn. Res. 2, 721–747 (2002)
Haralick R.M.: Statistical and structural approaches to texture. Proc. IEEE 67, 786–804 (1979)
Jimenez L.O., Landgrebe D.A.: Supervised classification in high dimensional space: geometrical, statistical, and asymptotical properties of multivariate data. IEEE Trans. Syst. Man, Cybern. C Appl. Rev. 28(1), 39–54 (1998)
Duda R.O., Hart P.E., Stork D.G.: Pattern Classification. Wiley, Hoboken (2001)
Kudo M., Sklansky J.: Comparison of algorithms that select features for pattern classifiers. Pattern Recognit. 33, 25–41 (2000)
Davies, S., Russell, S.: NP-completeness of searches for smallest possible feature sets. In: Proceedings of AAAI Fall Symposium Relevance, pp. 37–39 (1994)
Dash M., Liu H.: Feature selection for classification. Intell. Data Anal. Int. J. 1(3), 131–156 (1997)
Duin, R.P.W., Tax, D.M.J.: Classifier conditional posterior probabilities. In: Lecture Notes in Computer Science, vol. 1451, pp. 611–619, Springer, Berlin (1998)
Grimaldi, M., Cunningham, P., Kokaram, A.: An evaluation of alternative feature selection strategies and ensemble techniques of classifying music. Workshop in Multimedia Discovery and Mining at ECML/PKDD (2003)
Raymer M.L. et al.: Dimensionality reduction using genetic algorithms. IEEE Trans. Evol. Comput. 4(2), 164–171 (2000)
Tahir, M.A., Bouridane, A.: Novel Round-Robin Tabu search algorithm for prostate cancer classification and diagnosis using multispectral imagery. IEEE Trans. Inf. Technol. Biomed. 10(4), (2006)
Montgomery D.: Design and analysis of experiments, 4th edn. Wiley, New York (1997)
Fawcett, T.: ROC graphs: notes and practical considerations for researchers. Technical Report HPL-2003-4, HP Laboratories (2003)
Breiman L.: Bagging predictors. Mach. Learn. 24, 123–140 (1996)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Machine Learning: Proceedings of the Thirteenth International Conference, pp. 325–332 (1996)
Quinlan, J.R.: Bagging, boosting, and C4.5. In: Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 725–730 (1996)
Quinlan R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)
Yongguang, B., Ishii, N., Du, X.: Combining multiple k-nearest neighbour classifiers using different distance functions. In: Lectures Notes in Computer Science (LNCS 3177), 5th International Conference on Intelligence Data Engineering and Automation Learning (IDEAL 2004). Exeter, UK
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bouatmane, S., Roula, M.A., Bouridane, A. et al. Round-Robin sequential forward selection algorithm for prostate cancer classification and diagnosis using multispectral imagery. Machine Vision and Applications 22, 865–878 (2011). https://doi.org/10.1007/s00138-010-0292-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-010-0292-x