Abstract
Breast cancer is the most common form of cancer in women. Early diagnosis is necessary for effective treatment and therefore of crucial importance. Medical thermography has been demonstrated an effective and inexpensive method for detecting breast cancer, in particular in early stages and in dense tissue. In this paper, we propose a medical decision support system based on analysing bilateral asymmetries in breast thermograms. The underlying data is imbalanced, as the number of benign cases significantly exceeds that of malignant ones, which will lead to problems for conventional pattern recognition algorithms. To address this, we propose an ensemble classifier system which is based on the idea of Clustering and Selection. The feature space, which is derived from a series of image symmetry features, is partitioned in order to decompose the problem into a set of simpler decision areas. We then delegate a locally competent classifier to each of the generated clusters. The set of predictors is composed of both standard models as well as models dedicated to imbalanced classification, so that we are able to employ a specialised classifier to clusters that show high class imbalance, while maintaining a high specificity for other clusters. We demonstrate that our method provides excellent classification performance and that it statistically outperforms several state-of-the-art ensembles dedicated to imbalanced problems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Jones, B.F.: A reappraisal of infrared thermal image analysis for medicine. IEEE Trans. Medical Imaging 17(6), 1019–1027 (1998)
Anbar, N., Milescu, L., Naumov, A., Brown, C., Button, T., Carly, C., AlDulaimi, K.: Detection of cancerous breasts by dynamic area telethermometry. IEEE Engineering in Medicine and Biology Magazine 20(5), 80–91 (2001)
Head, J.F., Wang, F., Lipari, C.A., Elliott, R.L.: The important role of infrared imaging in breast cancer. IEEE Engineering in Medicine and Biology Magazine 19, 52–57 (2000)
Gautherie, M.: Thermobiological assessment of benign and maligant breast diseases. Am. J. Obstet. Gynecol. 147(8), 861–869 (1983)
Keyserlingk, J.R., Ahlgren, P.D., Yu, E., Belliveau, N., Yassa, M.: Functional infrared imaging of the breast. IEEE Engineering in Medicine and Biology Magazine 19(3), 30–41 (2000)
Kuncheva, L.I.: Combining pattern classifiers: Methods and algorithms. Wiley Interscience, New Jersey (2004)
Giacinto, G., Roli, F., Fumera, G.: Design of effective multiple classifier systems by clustering of classifiers. In: 15th Int. Conference on Pattern Recognition, vol. 2, pp. 160–163 (2000)
Marcialis, G.L., Roli, F.: Fusion of face recognition algorithms for video-based surveillance systems. In: Foresti, G., Regazzoni, C., Varshney, P. (eds.) Multisensor Surveillance Systems: The Fusion Perspective, pp. 235–250 (2003)
Rastrigin, L., Erenstein, R.H.: Method of Collective Recognition. Energoizdat, Moscow (1981)
Goebel, K., Yan, W.: Choosing classifiers for decision fusion. In: 7th Int. Conference on Information Fusion, pp. 563–568 (2004)
Ruta, D., Gabrys, B.: Classifier selection for majority voting. Information Fusion 6(1), 63–81 (2005)
Kuncheva, L.: Clustering-and-selection model for classifier combination. In: 4th Int. Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies, vol. 1, pp. 185–188 (2000)
Jackowski, K., Wozniak, M.: Algorithm of designing compound recognition system on the basis of combining classifiers with simultaneous splitting feature space into competence areas. Pattern Analysis and Applications 12(4), 415–425 (2009)
Qi, H., Snyder, W.E., Head, J.F., Elliott, R.L.: Detecting breast cancer from infrared images by asymmetry analysis. In: 22nd IEEE Int. Conference on Engineering in Medicine and Biology (2000)
Schaefer, G., Zavisek, M., Nakashima, T.: Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recognition 42(6), 1133–1137 (2009)
Zavisek, M., Drastich, A.: Thermogram classification in breast cancer detection. In: 3rd European Medical and Biological Engineering Conference, pp. 1727–1983 (2005)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research 16, 321–357 (2002)
Sun, Y., Wong, A.K.C., Kamel, M.S.: Classification of imbalanced data: A review. International Journal of Pattern Recognition and Artificial Intelligence 23(4), 687–719 (2009)
Chen, X., Wasikowski, M.: Fast: A roc-based feature selection metric for small samples and imbalanced data classification problems. In: ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, pp. 124–132 (2008)
Wang, S., Yao, X.: Diversity analysis on imbalanced data sets by using ensemble models. In: IEEE Symposium on Computational Intelligence and Data Mining, pp. 324–331 (2009)
Chawla, N.V., Lazarevic, A., Hall, L.O., Bowyer, K.W.: SMOTEBoost: improving prediction of the minority class in boosting. In: Lavrač, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) PKDD 2003. LNCS (LNAI), vol. 2838, pp. 107–119. Springer, Heidelberg (2003)
Błaszczyński, J., Deckert, M., Stefanowski, J., Wilk, S.: Integrating selective pre-processing of imbalanced data with Ivotes ensemble. In: Szczuka, M., Kryszkiewicz, M., Ramanna, S., Jensen, R., Hu, Q. (eds.) RSCTC 2010. LNCS, vol. 6086, pp. 148–157. Springer, Heidelberg (2010)
Liu, X., Wu, J., Zhou, Z.: Exploratory undersampling for class-imbalance learning. IEEE Trans. Systems, Man and Cybernetics - Part B: Cybernetics 39(2), 539–550 (2009)
Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31, 264–323 (1999)
Ling, C.X., Yang, Q., Wang, J., Zhang, S.: Decision trees with minimal costs. In: 21st Int. Conference on Machine Learning, pp. 544–551 (2004)
Alpaydin, E.: Combined 5 x 2 CV F test for comparing supervised classification learning algorithms. Neural Computation 11(8), 1885–1892 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Krawczyk, B., Schaefer, G., Zhu, S.Y. (2013). Breast Cancer Identification Based on Thermal Analysis and a Clustering and Selection Classification Ensemble. In: Imamura, K., Usui, S., Shirao, T., Kasamatsu, T., Schwabe, L., Zhong, N. (eds) Brain and Health Informatics. BHI 2013. Lecture Notes in Computer Science(), vol 8211. Springer, Cham. https://doi.org/10.1007/978-3-319-02753-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-02753-1_26
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02752-4
Online ISBN: 978-3-319-02753-1
eBook Packages: Computer ScienceComputer Science (R0)