Classificação de Lesões de Pele Utilizando Atributos de Cor e Textura
Abstract
Over the past three decades, more people have had skin cancer than all other cancers combined. However, this disease is curable if caught early. This work proposes an analysis of the components of HSV color model by using color and texture features. This extraction was made using medical images of skin lesions. The goal is to promote a classification with a lower error rate. In the tests, we used three classifiers: Support Vector Machine, MultiLayer Perceptron and Random Forest. The experimental results were satisfactory, reaching an accuracy rate of 0.9250 and Kappa index of 0.7541.
References
American Cancer Society (2015) “Cancer facts & figures 2015”, http://www.cancer.org/acs/groups/content/@editorial/documents/document/acspc-044552.pdf, abril.
Araújo, A. F. et al. (2012) “Análise e Caracterização de Lesões de Pele para Auxílio ao Diagnóstico Médico”. In Neves, L. A. P., Neto, H. V. e Gonzaga, A. (Eds.). Avanços em Visão Computacional. Paraná: omnipax. p. 27-46.
Baraldi, A. e Parmiggiani, F. (1995) “An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters”. Geoscience and Remote Sensing, IEEE Transactions on, v. 33, n. 2, p. 293-304.
Breiman, L. (2001) “Random forests”. Machine Learning, v. 45, n. 1, p. 5-32.
Camara, G. et al. (1996) “SPRING: Integrating remote sensing and GIS by object-oriented data modelling”. Computers & Graphics, v. 20, n. 3, p. 395-403.
Cavalcanti, P. G., Scharcanski, J. e Baranoski, G. V. G. (2013) “A two-stage approach for discriminating melanocytic skin lesions using standard cameras”. Expert Systems with Applications, v. 40, n. 10, p. 4054-4064.
Gonzalez, R. C. e Woods, R. E. (2010) “Processamento Digital de Imagens”. 3ª ed. São Paulo: Pearson Prentice Hall, 640 p.
Haralick, R., Shanmugam, K. e Dinstein, I. (1973) “Textural features for image classification”. Systems, Man and Cybernetics, IEEE Transactions on, n. 6, p. 610-621.
Haykin, S. (2008) “Neural Networks and Learning Machines”. 3ª ed. New Jersey: Prentice Hall, 936 p.
Mendonça, T. et al. (2013) “PH² - A dermoscopic image database for research and benchmarking”. In Engineering in Medicine and Biology Society (EMBC). 35th Annual International Conference of the IEEE. Osaka, Japan, p. 5437-5440.
Parolin, A., Herzer, E. e Jung C. R. (2010) “Semi-automated diagnosis of melanoma through the analysis of dermatological images”. In Graphics, Patterns and Images (SIBGRAPI), 2010 23rd SIBGRAPI Conference on. IEEE, p. 71–78.
Rosenfield, G. H. e Fitzpatrick-lins, K. A. (1986) “A coefficient of agreement as a measure of thematic classification accuracy”. Photogrammetric Engineering and Remote Sensing, v. 52, p. 223-227.
Skin Cancer Foundation (2015) “Skin cancer facts”, http://www.skincancer.org/skin-cancer-information/skin-cancer-facts#melanoma, abril.
Soares, H. B. (2008) “Análise e classificação de imagens de lesões da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte”. 180 f. Tese (Doutorado em Engenharia Elétrica) – Universidade Federal do Rio Grande do Norte.
World Health Organization (2015) “How common is skin cancer?”, http://www.who.int/uv/faq/skincancer/en/index1.html, abril.
Araújo, A. F. et al. (2012) “Análise e Caracterização de Lesões de Pele para Auxílio ao Diagnóstico Médico”. In Neves, L. A. P., Neto, H. V. e Gonzaga, A. (Eds.). Avanços em Visão Computacional. Paraná: omnipax. p. 27-46.
Baraldi, A. e Parmiggiani, F. (1995) “An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters”. Geoscience and Remote Sensing, IEEE Transactions on, v. 33, n. 2, p. 293-304.
Breiman, L. (2001) “Random forests”. Machine Learning, v. 45, n. 1, p. 5-32.
Camara, G. et al. (1996) “SPRING: Integrating remote sensing and GIS by object-oriented data modelling”. Computers & Graphics, v. 20, n. 3, p. 395-403.
Cavalcanti, P. G., Scharcanski, J. e Baranoski, G. V. G. (2013) “A two-stage approach for discriminating melanocytic skin lesions using standard cameras”. Expert Systems with Applications, v. 40, n. 10, p. 4054-4064.
Gonzalez, R. C. e Woods, R. E. (2010) “Processamento Digital de Imagens”. 3ª ed. São Paulo: Pearson Prentice Hall, 640 p.
Haralick, R., Shanmugam, K. e Dinstein, I. (1973) “Textural features for image classification”. Systems, Man and Cybernetics, IEEE Transactions on, n. 6, p. 610-621.
Haykin, S. (2008) “Neural Networks and Learning Machines”. 3ª ed. New Jersey: Prentice Hall, 936 p.
Mendonça, T. et al. (2013) “PH² - A dermoscopic image database for research and benchmarking”. In Engineering in Medicine and Biology Society (EMBC). 35th Annual International Conference of the IEEE. Osaka, Japan, p. 5437-5440.
Parolin, A., Herzer, E. e Jung C. R. (2010) “Semi-automated diagnosis of melanoma through the analysis of dermatological images”. In Graphics, Patterns and Images (SIBGRAPI), 2010 23rd SIBGRAPI Conference on. IEEE, p. 71–78.
Rosenfield, G. H. e Fitzpatrick-lins, K. A. (1986) “A coefficient of agreement as a measure of thematic classification accuracy”. Photogrammetric Engineering and Remote Sensing, v. 52, p. 223-227.
Skin Cancer Foundation (2015) “Skin cancer facts”, http://www.skincancer.org/skin-cancer-information/skin-cancer-facts#melanoma, abril.
Soares, H. B. (2008) “Análise e classificação de imagens de lesões da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte”. 180 f. Tese (Doutorado em Engenharia Elétrica) – Universidade Federal do Rio Grande do Norte.
World Health Organization (2015) “How common is skin cancer?”, http://www.who.int/uv/faq/skincancer/en/index1.html, abril.
Published
2015-07-20
How to Cite
DE MOURA, Nayara; MOURA, Gabriel; V. E SILVA, Romuere; SILVA, Emerson; VERAS, Rodrigo.
Classificação de Lesões de Pele Utilizando Atributos de Cor e Textura. In: BRAZILIAN SYMPOSIUM ON COMPUTING APPLIED TO HEALTH (SBCAS), 15. , 2015, Recife.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2015
.
p. 181-188.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2015.10378.
