Segmentação Semisupervisionada de Lesões de Pele com Uso de Superpixels
Resumo
Atualmente, a utilização de imagens em exames médicos tornou-se mais popular, pois consiste em um procedimento menos invasivo para os pacientes. Nesse trabalho é proposto um algoritmo semi-automático com o uso de superpixels para segmentar lesões de pele. O qual tem o como objetivo automatizar a segmentação das imagens sendo apenas necessário uma marcação prévia de algumas regiões pelo médico especialista. O PH2 contendo exatamente 200 imagens de arquivos publicos foi a base da nossa avaliação. Os resultados alcançados demonstram a aplicabilidade do nosso algoritmo, visto que, nos testes realizados o índice Kappa atingiu valores considerados ”Excelentes”.
Referências
[1] INCA, “Tipo - pele melanoma,” http://www.inca.gov.br/wps/wcm/connect/tiposdecancer/ site/home/pele melanoma, 2018, acessado em: 2018.
[2] M. E. C. Jacob Scharcanski, in Computer Vision Techniques for the Diagnosis of Skin Cancer. Spring, 2013.
[3] R. B. Oliveira, M. E. Filho, Z. Ma, J. P. Papa, A. S. Pereira, and J. M. R. Tavares, “Computational methods for the image segmentation of pigmented skin lesions: A review,” Computer Methods and Programs in Biomedicine, vol. 131, pp. 127–141, 2016.
[4] A. Pennisi, D. D. Bloisi, D. Nardi, A. R. Giampetruzzi, C. Mondinoc, and A. Facchiano, “Skin lesion image segmentation using delaunay triangulation for melanoma detection,” Computerized Medical Imaging and Graphics, vol. 52, pp. 89–103, 2016.
[5] J. S. M. Margarida Silveira, Jacinto C. Nascimento, “Comparison of segmentation methods for melanoma diagnosis in dermoscopy images, ieee.” Sel. Top. Signal Processing 3, 2009, pp. 929–936.
[6] R. C. GONZALEZ and R. E. WOODS, Digital image processing, 2nd ed. New Jersey: Prentice Hall, 2002.
[7] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, “Slic superpixels compared to state-of-the-art superpixel methods,” Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274–2282, 2012.
[8] Z. C. M. B F Nan, “Slico-based superpixel segmentation method with texture fusion,” Chinese Journal of Scientific Instrument, vol. 35, no. 3, pp. 527–534, 2014.
[9] R. M. Haralick, K. Shanmugam et al., “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, vol. 3, no. 6, pp. 610–621, 1973.
[10] L. Santos, R. Veras, R. Rabelo, K. Aires, and O. Aires, “A seeded fuzzy c-means based approach to automatic cup-to-disc ratio measurement,” in Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on. IEEE, 2017, pp. 1075–1080.
[11] T. Mendonc¸a, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, “Ph2-a dermoscopic image database for research and benchmarking,” in Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE. IEEE, 2013, pp. 5437–5440.
[12] J. R. Landis and G. G. Koch, “The measurement of observer agreement for categorical data,” biometrics, pp. 159–174, 1977.
[2] M. E. C. Jacob Scharcanski, in Computer Vision Techniques for the Diagnosis of Skin Cancer. Spring, 2013.
[3] R. B. Oliveira, M. E. Filho, Z. Ma, J. P. Papa, A. S. Pereira, and J. M. R. Tavares, “Computational methods for the image segmentation of pigmented skin lesions: A review,” Computer Methods and Programs in Biomedicine, vol. 131, pp. 127–141, 2016.
[4] A. Pennisi, D. D. Bloisi, D. Nardi, A. R. Giampetruzzi, C. Mondinoc, and A. Facchiano, “Skin lesion image segmentation using delaunay triangulation for melanoma detection,” Computerized Medical Imaging and Graphics, vol. 52, pp. 89–103, 2016.
[5] J. S. M. Margarida Silveira, Jacinto C. Nascimento, “Comparison of segmentation methods for melanoma diagnosis in dermoscopy images, ieee.” Sel. Top. Signal Processing 3, 2009, pp. 929–936.
[6] R. C. GONZALEZ and R. E. WOODS, Digital image processing, 2nd ed. New Jersey: Prentice Hall, 2002.
[7] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, “Slic superpixels compared to state-of-the-art superpixel methods,” Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274–2282, 2012.
[8] Z. C. M. B F Nan, “Slico-based superpixel segmentation method with texture fusion,” Chinese Journal of Scientific Instrument, vol. 35, no. 3, pp. 527–534, 2014.
[9] R. M. Haralick, K. Shanmugam et al., “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, vol. 3, no. 6, pp. 610–621, 1973.
[10] L. Santos, R. Veras, R. Rabelo, K. Aires, and O. Aires, “A seeded fuzzy c-means based approach to automatic cup-to-disc ratio measurement,” in Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on. IEEE, 2017, pp. 1075–1080.
[11] T. Mendonc¸a, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, “Ph2-a dermoscopic image database for research and benchmarking,” in Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE. IEEE, 2013, pp. 5437–5440.
[12] J. R. Landis and G. G. Koch, “The measurement of observer agreement for categorical data,” biometrics, pp. 159–174, 1977.
Publicado
16/10/2018
Como Citar
SANTOS, Elineide ; MOURA, Nayara ; VERAS, Rodrigo .
Segmentação Semisupervisionada de Lesões de Pele com Uso de Superpixels. In: ESCOLA REGIONAL DE INFORMÁTICA DO PIAUÍ (ERI-PI), 4. , 2018, Teresina.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2018
.
p. 250 - 255.
