Analysis of Shape-Based and Texture-Based Attributes in Classification of Mammographic Findings by Machine Learning Algorithms

• Matheus de Melo UFPB
• Andy Gajadhar UFPB
• Hugo de Oliveira UFPB
• Arnaldo de Andrade e Silva UFPB
• Leonardo Batista UFPB

DOI: https://doi.org/10.5753/sbcas.2015.10364

Resumo

Breast cancer is the most frequent cancer type among women. We present a method of classification of nodules (malignant or benign) found in mammograms using shape-based attributes and texture-based ones. Firstly, we built a test database, then we segmented and extracted a Gray Level Cooccurrence Matrix (GLCM) from each mammographic finding and analyzed texture-based and shape-based attributes. Finally, classification was performed through machine learning algorithms. Tests reached a maximum Correct Classification Rate (CCR) of 93.75%, when performed with the Radial Basis Function Network algorithm. The largest area under the ROC curve (AUC), 0.964, was achieved with the Multilayer Perceptron algorithm.

Referências

Acharya, U., Vinitha Sree, S., Saba, L., Molinari, F., Guerriero, S., and Suri, J. (2012). Ovarian tumor characterization and classification: A class of gynescan systems. In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, pages 4446–4449. IEEE.

Alam, S., Feleppa, E., Rondeau, M., Kalisz, A., and Garra, B. (2013). Computer-aided diagnosis of solid breast lesions using an ultrasonic multi-feature analysis procedure. Bangladesh Journal of Medical Physics, 4(1):1–10.

Alto, H., Rangayyan, R. M., and Desautels, J. L. (2005). Content-based retrieval and analysis of mammographic masses. Journal of Electronic Imaging, 14(2):023016– 023016.

Arora, R. and Suman, S. (2012). Comparative analysis of classification algorithms on different datasets using weka. International Journal of Computer Applications, 54(13):21–25.

Boujelben, A., Chaabani, A. C., Tmar, H., and Abid, M. (2009). Feature extraction from contours shape for tumor analyzing in mammographic images. In Digital Image Computing: Techniques and Applications, 2009. DICTA’09., pages 395–399. IEEE.

Braz Junior, G., Da Rocha, S. V., Gattass, M., Silva, A. C., and De Paiva, A. C. (2013). A mass classification using spatial diversity approaches in mammography images for false positive reduction. Expert systems with applications, 40(18):7534–7543.

Duarte, Y. A. S., Do Nascimento, M. Z., and Oliveiras, D. L. L. (2013). Algoritmo de extração de textura baseado em wavelet e clbp para classificação de les˜oes em mamogramas. In XIII Workshop de Informática Médica, pages 174–183.

Fraschini, M. (2011). Mammographic masses classification: novel and simple signal analysis method. Electronics letters, 47(1):14–15.

Gonzale, R. C., Woods, R. E., and Eddins, S. L. (2003). Digital Image Processing Using MATLAB. Pearson Prentice Hall, New Jersey, United States.

Haralick, R. M., Shanmugam, K., and Dinstein, I. H. (1973). Textural features for image classification. Systems, Man and Cybernetics, IEEE Transactions on, (6):610–621.

Huang, Y. and Chen, D. (2005). Support vector machines in sonography: application to decision making in the diagnosis of breast cancer. Clinical imaging, 29(3):179–184.

Jalalian, A., Mashohor, S. B., Mahmud, H. R., Saripan, M. I. B., Ramli, A. R. B., and Karasfi, B. (2013). Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. Clinical imaging, 37(3):420–426.

Kallergi, M. (2004). Computer-aided diagnosis of mammographic microcalcification clusters. Medical Physics, 31(2):314–326.

Ke, L., Mu, N., and Kang, Y. (2010). Mass computer-aided diagnosis method in mammogram based on texture features. In Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on, volume 1, pages 354–357. IEEE.

Lan, Y., Ren, H., Zhang, Y., and Yu, H. (2012). Similarity in mammography cad using cbir approach: A validation study. In Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2012 4th International Conference on, volume 2, pages 373–376. IEEE.

Li, X., Williams, S., and Bottema, M. J. (2014). Texture and region dependent breast cancer risk assessment from screening mammograms. Pattern Recognition Letters, 36:117–124.

Martí, R., Oliver, A., Raba, D., and Freixenet, J. (2007). Breast skin-line segmentation using contour growing. In Pattern Recognition and Image Analysis, pages 564–571. Springer.

Mudigonda, N. R., Rangayyan, R. M., and Desautels, J. L. (2000). Gradient and texture analysis for the classification of mammographic masses. Medical Imaging, IEEE Transactions on, 19(10):1032–1043.

Rangayyan, R. M., El-Faramawy, N. M., Desautels, J. L., and Alim, O. A. (1997). Measures of acutance and shape for classification of breast tumors. Medical Imaging, IEEE Transactions on, 16(6):799–810.

Shapiro, L. G. and Stockman, G. (2001). Computer Vision. pearson Prentice Hall, New Jersey, United States.

Society, A. C. (2014). Cancer effects & figures. American Cancer Society.

Wang, Z., Yu, G., Kang, Y., Zhao, Y., and Qu, Q. (2014). Breast tumor detection in digital mammography based on extreme learning machine. Neurocomputing, 128(0):175 – 184.

Weiqiang, Z., Xiangmin, X., andWei, H. (2008). Shape and boundary analysis for classification of breast masses. In Computational Intelligence and Design, 2008. ISCID’08. International Symposium on, volume 2, pages 42–46. IEEE.

Witten, I. H., Frank, E., and Hall, M. A. (2011). Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann.