Abstract
In the field of breast cancer research, and more than ever, new computer aided diagnosis based systems have been developed aiming to reduce diagnostic tests false-positives. Within this work, we present a data mining based approach which might support oncologists in the process of breast cancer classification and diagnosis. The present study aims to compare two breast cancer datasets and find the best methods in predicting benign/malignant lesions, breast density classification, and even for finding identification (mass / microcalcification distinction). To carry out these tasks, two matrices of texture features extraction were implemented using Matlab, and classified using data mining algorithms, on WEKA. Results revealed good percentages of accuracy for each class: 89.3 to 64.7 % - benign/malignant; 75.8 to 78.3 % - dense/fatty tissue; 71.0 to 83.1 % - finding identification. Among the different tests classifiers, Naive Bayes was the best to identify masses texture, and Random Forests was the first or second best classifier for the majority of tested groups.
Similar content being viewed by others
References
Ferlay, J., Soerjomataram, I., Dikshit, R., Eser, S., Mathers, C., Rebelo, M., Parkin, D.M., Forman, D., and Bray, F., Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012. Int J Cancer. 136(5):E359–E386, 2015. doi:10.1002/ijc.29210.
American Cancer Society, Cancer facts and figs. 2016. American Cancer Society, Atlanta, Ga, 2016.
de Oliveira, J.E., Machado, A.M., Chavez, G.C., Lopes, A.P., Deserno, T.M., and Araujo Ade, A., MammoSys: A content-based image retrieval system using breast density patterns. Comput Methods Prog Biomed. 99(3):289–297, 2010. doi:10.1016/j.cmpb.2010.01.005.
Matheus, B., and Schiabel, H., A CADx scheme in mammography: considerations on a novel approach. In: ADVCOMP 2013. The Seventh International Conference on Advanced Engineering Computing and Applications in Sciences. 2013:15–18, 2013.
Moura, D.C., and Guevara Lopez, M.A., An evaluation of image descriptors combined with clinical data for breast cancer diagnosis. Int J Comput Assist Radiol Surg. 8(4):561–574, 2013. doi:10.1007/s11548-013-0838-2.
Dong, M., Lu, X., Ma, Y., Guo, Y., Ma, Y., and Wang, K., An efficient approach for automated mass segmentation and classification in mammograms. J Digit Imaging. 28(5):613–625, 2015. doi:10.1007/s10278-015-9778-4.
Ogiela, L., Computational intelligence in cognitive healthcare information systems. In: Bichindaritz, I., Vaidya, S., Jain, A., and Jain, L.C. (Eds.), Computational intelligence in healthcare 4: Advanced methodologies. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp. 347–369, 2010. doi:10.1007/978-3-642-14464-6_16.
Ogiela, L., Semantic analysis and biological modelling in selected classes of cognitive information systems. Math Comput Model. 58(5–6):1405–1414, 2013. doi:10.1016/j.mcm.2012.12.001.
Pérez, N., Silva, A., and Ramos, I., Ensemble features selection method as tool for breast cancer classification. Int J Image Min. 1(2–3):224–244, 2015. doi:10.1504/IJIM.2015.073019.
Kuusisto, F., Dutra, I., Elezaby, M., Mendonça, E.A., Shavlik, J., and Burnside, E.S., Leveraging expert knowledge to improve machine-learned decision support systems. AMIA Summits Transl Sci Proceed. 2015:87–91, 2015.
Diz, J., Marreiros, G., and Freitas, A., Using data mining techniques to support breast cancer diagnosis. New Contributions in Information Systems and Technologies. Springer, In, pp. 689–700, 2015. doi:10.1007/978-3-319-16486-1_68.
Tseng, W.T., Chiang, W.F., Liu, S.Y., Roan, J., and Lin, C.N., The application of data mining techniques to oral cancer prognosis. J Med Syst. 39(5):59, 2015. doi:10.1007/s10916-015-0241-3.
Malucelli, A., Stein Junior, A., Bastos, L., Carvalho, D., Cubas, M.R., and Paraíso, E.C., Classification of risk micro-areas using data mining. Rev Saude Publica. 44(2):292–300, 2010. doi:10.1590/S0034-89102010000200009.
Force UPST, Screening for breast cancer: U.S. Preventive Services Task Force recommendation statement. Ann Intern Med. 151(10):716–726 , 2009. doi:10.7326/0003-4819-151-10-200911170-00008.W-236
D’Orsi, C.J., Sickles, E.A., Mendelson, E.B., Morris, E.A., et al., ACR BI-RADS® atlas, breast imaging reporting and data system. Reston, VA, American College of Radiology, 2013.
Boyd, N.F., Martin, L.J., Bronskill, M., Yaffe, M.J., Duric, N., and Minkin, S., Breast tissue composition and susceptibility to breast cancer. J Nat Cancer Inst. 102(16):1224–1237, 2010. doi:10.1093/jnci/djq239.
Gierach, G.L., Ichikawa, L., Kerlikowske, K., Brinton, L.A., Farhat, G.N., Vacek, P.M., Weaver, D.L., Schairer, C., Taplin, S.H., and Sherman, M.E., Relationship between mammographic density and breast cancer death in the breast cancer surveillance consortium. J Nat Cancer Inst. 104(16):1218–1227, 2012. doi:10.1093/jnci/djs327.
López MAG, Posada N, Moura DC, Pollán RR, Valiente JMF, Ortega CS, Solar M, Diaz-Herrero G, Ramos I, Loureiro J, Fernandes TC, Araújo BMF. (2012) BCDR: a breast cancer digital repository. In: 15th International Conference on Experimental Mechanics, FEUP-EURASEM-APAET, Porto/Portugal, 22–27 July 2012. ISBN: 978–972–8826-26-02.
Suri JS, Wilson DL, Laxminarayan S (2005) Handbook of biomedical image analysis, vol 2. Springer Science & Business Media. doi:10.1007/b104806
Carneiro P, Patrocinio (2014) A Análise de atributos de intensidade e textura na classificação de densidade mamária. In: XXIV Congresso Brasileiro de Engenharia Biomédica – CBEB 2014, pp 634–637
Meselhy Eltoukhy, M., Faye, I., and Belhaouari Samir, B., A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation. Comput Biol Med. 42(1):123–128, 2012. doi:10.1016/j.compbiomed.2011.10.016.
Mohanty, A.K., Senapati, M.R., Beberta, S., and Lenka, S.K., Texture-based features for classification of mammograms using decision tree. Neural Comput Applic. 23(3–4):1011–1017, 2013. doi:10.1007/s00521-012-1025-z.
Nanni, L., Brahnam, S., Ghidoni, S., Menegatti, E., and Barrier, T., Different approaches for extracting information from the co-occurrence matrix. PloS one. 8(12):e83554, 2013. doi:10.1371/journal.pone.0083554.
Hsu, J.L., Hung, P.C., Lin, H.Y., and Hsieh, C.H., Applying under-sampling techniques and cost-sensitive learning methods on risk assessment of breast cancer. J Med Syst. 39(4):210, 2015. doi:10.1007/s10916-015-0210-x.
Pérez N, Guevara MA, Silva A, Ramos I, Loureiro J (2014) Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. In: Computer Science and Information Systems (FedCSIS), 2014 Federated Conference on. IEEE, pp 209–217. doi:10.15439/2014F249
Bueno, G., Vállez, N., Déniz, O., Esteve, P., Rienda, M.A., Arias, M., and Pastor, C., Automatic breast parenchymal density classification integrated into a CADe system. Int J Comput Assist Radiol Surg. 6(3):309–318, 2011. doi:10.1007/s11548-010-0510-z.
Ramos-Pollán, R., Guevara-López, M.A., Suárez-Ortega, C., Díaz-Herrero, G., Franco-Valiente, J.M., Rubio-del-Solar, M., González-de-Posada, N., Vaz, M.A.P., Loureiro, J., and Ramos, I., Discovering mammography-based machine learning classifiers for breast cancer diagnosis. J Med Syst. 36(4):2259–2269, 2012. doi:10.1007/s10916-011-9693-2.
Oliver A, Freixenet J, Martí R, Zwiggelaar R (2006) A comparison of breast tissue classification techniques. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2006. Springer, pp 872–879. doi:10.1007/11866763_107
Lesniak, J., Hupse, R., Blanc, R., Karssemeijer, N., and Székely, G., Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography. Phys Med Biol. 57(16):5295–5307, 2012. doi:10.1088/0031-9155/57/16/5295.
Janitza, S., Strobl, C., and Boulesteix, A.-L., An AUC-based permutation variable importance measure for random forests. BMC bioinformatics. 14:119, 2013. doi:10.1186/1471-2105-14-119.
Luo, S.T., and Cheng, B.W., Diagnosing breast masses in digital mammography using feature selection and ensemble methods. J Med Syst. 36(2):569–577, 2012. doi:10.1007/s10916-010-9518-8.
Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, San Francisco. ISBN:0120884070
Castella, C., Kinkel, K., Eckstein, M.P., Sottas, P.-E., Verdun, F.R., and Bochud, F.O., Semiautomatic mammographic parenchymal patterns classification using multiple statistical features. Acad Radiol. 14(12):1486–1499, 2007. doi:10.1016/j.acra.2007.07.014.
Fonseca, J., Pre-CADs in breast cancer. FEUP, MSc Thesis in Engenharia Eletrotécnica e de Computadores, 2013.
Benndorf, M., Kotter, E., Langer, M., Herda, C., Wu, Y., and Burnside, E.S., Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon. Eur Radiol. 25(6):1768–1775, 2015. doi:10.1007/s00330-014-3570-6.
Timmers, J.M.H., van Doorne-Nagtegaal, H.J., Verbeek, A.L.M., den Heeten, G.J., and Broeders, M.J.M., A dedicated BI-RADS training programme: effect on the inter-observer variation among screening radiologists. Eur J Radiol. 81(9):2184–2188, 2012. doi:10.1016/j.ejrad.2011.07.011.
Obenauer, S., Hermann, K.P., and Grabbe, E., Applications and literature review of the BI-RADS classification. Eur Radiol. 15(5):1027–1036, 2005. doi:10.1007/s00330-004-2593-9.
Fischer EA, Lo JY, Markey MK (2004) Bayesian networks of BI-RADS descriptors for breast lesion classification. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings 4:3031–3034. issn: 0589–1019
Elter, M., Schulz-Wendtland, R., and Wittenberg, T., The prediction of breast cancer biopsy outcomes using two CAD approaches that both emphasize an intelligible decision process. Med Phys. 34(11):4164–4172, 2007. doi:10.1118/1.2786864.
Lacquement, M.A., Mitchell, D., and Hollingsworth, A.B., positive predictive value of the breast imaging reporting and data system. J Am Coll Surg. 189(1):34–40, 1999. doi:10.1016/S1072-7515(99)00080-0.
Burnside, E.S., Davis, J., Chhatwal, J., Alagoz, O., Lindstrom, M.J., Geller, B.M., Littenberg, B., Shaffer, K.A., Kahn Jr., C.E., and Page, C.D., Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings. Radiology. 251(3):663–672, 2009. doi:10.1148/radiol.2513081346.
Mandelson, M.T., Oestreicher, N., Porter, P.L., White, D., Finder, C.A., Taplin, S.H., and White, E., Breast density as a predictor of mammographic detection: comparison of interval- and screen-detected cancers. J Natl Cancer Ins. 92(13):1081–1087, 2000. doi:10.1093/jnci/92.13.1081.
Acknowledgments
The authors would like to thank the Breast Cancer Digital Repository Consortium of University of Porto and in particular Doctor Mário Vaz and Doctor Miguel Guevara who allowed the access to the BCDR dataset.
This work is supported by FEDER Funds through COMPETE program and by National Funds through FCT under the project UID/EEA/00760/2013.
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on Systems-Level Quality Improvement
Rights and permissions
About this article
Cite this article
Diz, J., Marreiros, G. & Freitas, A. Applying Data Mining Techniques to Improve Breast Cancer Diagnosis. J Med Syst 40, 203 (2016). https://doi.org/10.1007/s10916-016-0561-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-016-0561-y