Abstract
Skin cancer is the most common type of cancer. Melanoma is a malign type of skin cancer responsible for several deaths in the world. An early diagnosis increases the probability of cure. Dermatoscopy is one of the procedures for such diagnosis. Using dermatoscopy, it is possible to recognize skin structures that are not visible to the human sight. The dermatoscope zooms in images for a more precise diagnostic. Although less efficient than the analysis of experts, it is possible to find several proposals for the automatic classification of skin lesions in the literature, some of them using image characteristics of shape, colour, and texture. Our proposal aims at supporting doctors using dermatoscopy for the automatic classification of skin lesions. In our experiments, we used 21 classification algorithms with different inducing paradigms. The best results were obtained using the FuzzyDT algorithm, based on a set of image characteristics related to shape, colour, and texture. One of the main contributions of this proposal, is the characteristic selection procedure using FuzzyDT, which obtained high accuracy, as well as a dataset of preprocessed cancer skin images. The proposal is detailed and the results are presented and discussed.
We thank CAPES for the financial support.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
WHO: World Health Organization (2020). https://www.who.int/news-room/q-a-detail/protecting-oneself-from-skin-cancer. Accessed Oct 2020
INCA: Brazilian National Cancer Institute (2020). https://www.inca.gov.br/. Accessed Oct 2020
Soyer, H., Smolle, J., Kerl, H., Stettnre, H.: Early diagnosis of malignant melanoma by surface microscopy. Lancet 330(8562), 803 (1987)
Alpaydin, E.: Introduction to Machine Learning: Adaptive Computation and Machine Learning. 3 edn. MIT Press, Cambridge (2014)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press - Claredon Press (2004)
Senge, R., HĂ¼llermeier, E.: Fast fuzzy pattern tree learning for classification. IEEE Trans. Fuzzy Syst. 23(6), 2024–2033 (2015)
Cintra, M.E., Monard, M.C., Camargo, H.A.: FCA-Based Rule Generator, a framework for the genetic generation of fuzzy classification systems using formal concept analysis. In: Proceedings of the FuzzIEEE 2015 - IEEE International Conference on Fuzzy Systems, vol. 1, pp. 1–8. IEEE (2015)
Quinlan, J.R.: C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco (1993). http://portal.acm.org/citation.cfm?id=152181
Cintra, M.E., Camargo, H.A.: Feature subset selection for fuzzy classification methods. In: International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems - IPMU, vol. 80, pp. 318–327 (2010)
Pedrycz, W., Sosnowski, Z.A.: Genetically optimized fuzzy decision trees. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 35(3), 633–641 (2005)
Klir, G.J., Yuan, B.: Fuzzy Sets and Fuzzy Logic - Theory and Applications. Prentice-Hall, Upper Saddle River (1995)
Cintra, M.E., Camargo, H.A., Monard, M.C.: Implementation of the fuzzyDT algorithm. https://www.researchgate.net/publication/341069396_FuzzyDT (2020)
Celebi, M.E., Zornberg, A.: Automated quantification of clinically significant colors in dermoscopy images and its application to skin lesion classification. IEEE Syst. J. 8(3), 980–984 (2014)
Abuzaghleh, O., Barkana, B.D., Faezipour, M.: SKINcure: a real time image analysis system to aid in the malignant melanoma prevention and early detection. In: Southwest Symposium on Image Analysis and Interpretation (SSIAI), IEEE (2014)
Oliveira, R.B., Junior, C.R.D.C., Guido, R.C., Marranghello, N., Pereira, A.S.: ClassificaĂ§Ă£o de assimetria em lesoes de pele por meio de imagens usando maquina de vetor de suporte. VIII Workshop de VisĂ£o Computacional (2012)
Ganzeli, H.S., Bottesini, J.G., Paz, L.O., Ribeiro, M.F.S.: SKAN: skin scanner - system for skin cancer detection using adaptive techniques. IEEE Latin Am. Trans. 9(2), 206–212 (2011)
Canny, J.: A computation approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986)
Ruiz, D., Berenguer, V., Soriano, A., SĂ¡nchez, B.: A decision support system for the diagnosis of melanoma: a comparative approach. Exp. Syst. Appl. 38(12), 15217–15223 (2011). http://www.sciencedirect.com/science/article/pii/S0957417411008633
Maurya, R., Singh, S.K., Maurya, A.K., Kumar, A.: Glcm and multi class support vector machine based automated skin cancer classification. In: 2014 International Conference on Computing for Sustainable Global Development (INDIACom), pp. 444–447 (2014)
Dermquest: Dermquest. https://dermaquestinc.com/ (Mar 2019)
Dermnet: Dermnet Skin Disease Atlas. http://www.dermnet.com/images/Melanoma-Skin-Cancer-Nevi-and-Moles/ (2020)
Albay, E., Kamaşak, M.E.: Improved classification of skin lesions using shape and color features. In: 2016 24th Signal Processing and Communication Application Conference (SIU), pp. 733–736 (2016)
Maia, L.B., et al.: Evaluation of melanoma diagnosis using deep features. In: 2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 1–4 (2018)
Mendonça, T., Ferreira, P.M., Marques, J.S., Marcal, A.R.S., Rozeira, J.: Ph2 - a dermoscopic image database for research and benchmarking. In: 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 5437–5440 (2013). http://www.fc.up.pt/addi/ph2database.html
Vieira, C., Moraes, W.: MATLAB - Curso Completo. FCA, 1 edn. (2013)
Facelli, K., Lorena, A.C., Gama, J., Carvalho, A.C.P.L.F.: InteligĂªncia Artificial: uma abordagem de aprendizado de mĂ¡quina. LTC, 1 edn. (2011)
Witten, I.H., Frank, E., Hall, M.A.: Data Mining: Practical Machine Learning Tools and Techniques, 3rd edn. Morgan Kaufmann, Amsterdam (2011)
HĂ¼hn, J., HĂ¼llermeier, E.: Furia: an algorithm for unordered fuzzy rule induction. Data Min. Knowl. Disc. 19(3), 293–319 (2009)
Sanz, J., FernĂ¡ndez, A., Bustince, H., Herrera, F.: IVTURS: a linguistic fuzzy rule-based classification system based on a new interval-valued fuzzy reasoning method with tuning and rule selection. IEEE Trans. Fuzzy Syst. 21(3), 399–411 (2013)
Maia, H.W.: Dataset with extracted characteristics of skin cancer images. http://dx.doi.org/10.13140/RG.2.2.12759.09120 (2020)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Maia, H.W., Cintra, M.E. (2021). Skin Cancer Automatic Detection Based on Image Characteristics of Shape, Colour, and Texture. In: Abraham, A., et al. Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2020). SoCPaR 2020. Advances in Intelligent Systems and Computing, vol 1383. Springer, Cham. https://doi.org/10.1007/978-3-030-73689-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-73689-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73688-0
Online ISBN: 978-3-030-73689-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)