Uma Análise Híbrida para Identificação de Câncer de Mama usando Sinais Térmicos

• Lincoln Silva UFF
• Giomar Oliveira UFF
• Tiago Borchartt UFF
• Roger Resmini UFF
• Alair Santos UFF
• Cristina Fontes UFF
• Débora Muchaluat-Saade UFF
• Aura Conci UFF

DOI: https://doi.org/10.5753/sbcas.2015.10367

Abstract

Breast cancer is the second most common cancer in the world. Currently, there are no effective methods to prevent this disease. However, diagnosis and treatment in early stages increase cure chances. Since cancerous tissue temperature is generally higher than healthy surrounding tissues, thermography is an option to be considered in strategies to identify this cancer. This paper proposes a new hybrid breast dynamic thermography analysis method in order to identify patients with breast cancer. Images of dynamic thermography are processed in order to generate thermal signals using both breasts. These signals are analyzed by supervised and unsupervised learning techniques. In the test phase, five classification models were generated, using Bayesian networks, neural networks, decision tables, bagging and random forests. Performed tests show that the method presented in this paper is able to identify patients with breast cancer and that Bayesian network is the best learning technique presenting 100% accuracy. In addition, we have obtained an average of 93.63% accuracy among all classification models.

References

Amalu,W. C. (2004). Nondestructive testing of the human breast: The validity of dynamic stress testing in medical infrared breast imaging. Engineering in Medicine and Biology Society, 1:1174–1177.

Bezerra, L., Oliveira, M., Rolim, T., Conci, A., Santos, F., Lyra, P., and Lima, R. (2013). Estimation of breast tumor thermal properties using infrared images. Signal Processing, 93(10):2851–2863.

Bolshakova, N. and Azuaje, F. (2003). Cluster validation techniques for genome expression data. Signal Processing, 83(4):825–833.

Bolshakova, N. and Azuaje, F. (2006). Estimating the number of clusters in dna microarray data. Methods of Information in Medicine, 45(2):153–157.

Borchartt, T. B., Conci, A., Lima, R. C. F., Resmini, R., and Sanchez, A. (2013). Breast thermography from an image processing viewpoint: A survey. Signal Processing, 93:2785–2803.

Borchartt, T. B., Resmini, R., Motta, L. S., Clua, E. W., Conci, A., Viana, M. J., Santos, L. C., Lima, R. C., and Sanchez, A. (2012). Combining approaches for early diagnosis of breast diseases using thermal imaging. International Journal of Innovative Computing and Applications, 4(3-4):163–183.

Cali´nski, T. and Harabasz, J. (1974). A dendrite method for cluster analysis. Communications in Statistics, 3(1):1–27.

Chen, G., Jaradat, S. A., Banerjee, N., Tanaka, T. S., Ko, M. S. H., and Zhang, M. Q. (2002). Evaluation and comparison of clustering algorithms in anglying es cell gene expression data. Statistica Sinica, 12:241–262.

Davies, D. L. and Bouldin, D. W. (1979). A cluster separation measure. Pattern Analysis and Machine Intelligence, IEEE Transactions on, PAMI-1(2):224–227.

Flir (2015). Sc620 infrared camera system. http://www.flir.com/cs/apac/en/view/?id=41413. acessado em 20 de abril de 2013.

Gerasimova, E., Audit, B., Roux, S., Khalil, A., Gileva, O., Argoul, F., Naimark, O., and Arneodo, A. (2014). Wavelet-based multifractal analysis of dynamic infrared thermograms to assist in early breast cancer diagnosis. Frontiers in Physiology, 5(176).

Gerasimova, E., Audit, B., Roux, S. G., Khalil, A., Argoul, F., Naimark1, O., and Arneodo, A. (2013). Multifractal analysis of dynamic infrared imaging of breast cancer. EPL (Europhysics Letters), 104(6):68001–p1–68001–p6.

Gerasimova, E., Plekhov, O., Yu.Bayandin, O.Naimark, and G.Freynd (2012). Identification of breast cancer using analysis of thermal signals by nonlinear dynamics methods. International Conference on Quantitative InfraRed Thermography. , 11-14 June, Naples-Italy.

Goshtasby, A. A. (2005). 2-D and 3-D Image Registration: for Medical, Remote Sensing, and Industrial Applications. Wiley, New Jersey.

Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The weka data mining software: An update. SIGKDD Explorations, 11(1):10–18.

Hall, M. A. (1999). Correlation-based Feature Selection for Machine Learning. PhD thesis, Department of Computer Science, The University of Waikato, Hamilton, New- Zealand.

Hall, M. A. and Holmes, G. (2003). Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans. on Knowl. and Data Eng., 15(6):1437–1447.

Han, J. and Kamber, M. (2006). Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers, Burlington, MA 01803, USA, 2rd ed edition.

Hartigan, J. (1985). Statistical theory in clustering. Journal of Classification, 2(1):63–76.

Herman, C. (2013). The role of dynamic infrared imaging in melanoma diagnosis. Expert Review of Dermatology, 8(2):177–184.

Krzanowski,W. J. and Lai, Y. T. (1988). A criterion for determining the number of groups in a data set using sum-of-squares clustering. Biometrics, 44(1):23–34.

Lewis, J., Ackerman, M., and Sa, V. (2012). Human cluster evaluation and formal quality measures: A comparative study. Proc. 34th Conf. of the Cognitive Science Society CogSci.

MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. University of California Press, pages 281–297.

Myronenko, A. and Song, X. (2010). Intensity-based image registration by minimizing residual complexity. Medical Imaging, IEEE Transactions on, 29(11):1882–1891.

Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20(0):53–65.

Silva, L. F., Marques, R. S., Carvalho, G. S., Santos, M. L. O., Fontes, C. A. P., Santos, A.

A. S. M. D., and Conci, A. (2013). Protocolo de captura de imagens térmicas da mama para construção de um banco público de exames. Encontro Nacional de Engenharia Biomecânica.

Silva, L. F., Olivera, G. O. S., Galvao, S., Silva, J. B., Santos, A. A. S. M. D., Muchaluat- Saade, D. C., and Conci, A. (2014a). Análise de séries temporais de sinais térmicos da mama para detecção de anomalias. WIM-XIV Workshop de Informática Médica-Anais CSBC, pages 1818–1827.

Silva, L. F., Saade, D. C. M., Sequeiros, G. O., Silva, A. C., Paiva, A. C., Bravo, R. S., and Conci, A. (2014b). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1):92–100.

Witten, I. H., Eibe, F., and Hall, M. A. (2011). Data mining: practical machine learning tools and techniques. Morgan Kaufmann Publishers, Burlington, MA 01803, USA, 3rd ed edition.