Diagnóstico de Melanoma através de Padrões Binários Locais e Decomposição Espacial

• Pedro Santos UFMA
• Lucas Maia UFMA
• Geraldo Braz UFMA
• João Almeida UFMA
• Anselmo Paiva UFMA

Abstract

Skin cancer is the cancer form with the highest incidence in the population, and although melanoma is a small fraction of these incidences, it is usually the most severe type of skin cancer. Several types of approaches in the area of automatic detection and diagnosis of this type of disease are being explored as pattern recognition techniques along with machine learning. This work aims to study binary local patterns associated with the spatial decomposition of the lesion region for the automatic detection of melanoma. The study, which compares the performance of the application of three different classifiers to the problem, achieves the best 0.88 result of accuracy and accuracy for the PH2 base demonstrating the methodology’s efficiency to the problem of melanoma detection.

References

Ahmed, F., Hossain, E., Bari, A., and Shihavuddin, A. (2011). Compound local binary pattern (clbp) for robust facial expression recognition. In Computational Intelligence and Informatics (CINTI), 2011 IEEE 12th International Symposium on, pages 391– 395, Obuda University, Budapest, Hungary. IEEE.

Bratkova, M., Boulos, S., and Shirley, P. (2009). orgb: a practical opponent color space for computer graphics. IEEE Computer Graphics and Applications, 29(1).

Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.

Cortes, C. and Vapnik, V. (1995). Support vector machine. Machine learning, 20(3):273– 297.

Hering, E. (1880). Zur Erkl¨arung der Farbenblindheit aus der Theorie der Gegenfarben, volume 1. Tempsky.

Masters, B. R., Gonzalez, R. C., andWoods, R. (2009). Digital image processing. Journal of biomedical optics, 14(2):029901.

Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R., and Rozeira, J. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, pages 5437–5440. IEEE.

Ng, A. Y. and Jordan, M. I. (2002). On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In Advances in neural information processing systems, pages 841–848.

Ojala, T., Pietik¨ainen, M., and Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51– 59.

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1):62–66.

Rosado, L. F. C. M. G. (2009). Sistema automático para diagnóstico de les˜oes cutâneas baseado em imagens dermoscópicas. Universidade do Estado do Rio Grande do Norte, Biblioteca Central Orlando Teixeira, BR-RN.

Soares, H. B. (2008). Análise e classificação de imagens de les˜oes da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte.

Teague, M. R. (1980). Image analysis via the general theory of moments. JOSA, 70(8):920–930.