Classification of Melanoma Presence and Thickness Based on Computational Image Analysis

详细信息    查看全文

• 关键词：Melanoma ; Feature extraction ; Dermoscopic image ; Computer vision ; Machine learning ; Multi ; class ; Ordinal classification ; Imbalanced classification
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9648
• 期：1
• 页码：427-438
• 全文大小：606 KB
• 参考文献：1.Institute, N.C.:Seer stat fact sheets: melanoma of the skin (2015). http://​seer.​cancer.​gov/​statfacts/​html/​melan.​html . Accessed 15 December 2015
  2.For Research on Cancer. World Health Organization, I.A.:Cancer factsheet. Malignant melanoma of skin (2015). http://​eco.​iarc.​fr/​eucan/​Cancer.​aspx?​Cancer=​20 . Accessed 15 Dec 2015
  3.Pizzichetta, M., Argenziano, G., Talamini, R., Piccolo, D., Gatti, A., Trevisan, G., Sasso, G., Veronesi, A., Carbone, A., Peter Soyer, H.: Dermoscopic criteria for melanoma in situ are similar to those for early invasive melanoma. Cancer 91, 992–997 (2001)CrossRef
  4.Herman, C.: Emerging technologies for the detection of melanoma: achieving better outcomes. Clin. Cosmet. Invest. Dermatol. 5, 195–212 (2012)CrossRef
  5.Maglogiannis, I., Doukas, C.N.: Overview of advanced computer vision systems for skin lesions characterization. IEEE Trans. Inf.Technol. Biomed. 13, 721–733 (2009)CrossRef
  6.Garnavi, R., Aldeen, M., Bailey, J.: Computer-aided diagnosis of melanoma using border- and wavelet-based texture analysis. IEEE Trans. Inf. Technol. Biomed. 16, 1239–1252 (2012)CrossRef
  7.Celebi, M., Kingravi, H., Uddin, B., Iyatomi, H., Aslandogan, Y., Stoecker, W., Moss, R.: A methodological approach to the classification of dermoscopy images. Comput. Med. Imaging Graph. 31, 362–373 (2007)CrossRef
  8.Rubegni, P., Cevenini, G., Sbano, P., Burroni, M., Zalaudek, I., Risulo, M., Dell’Eva, G., Nami, N., Martino, A., Fimiani, M.: Evaluation of cutaneous melanoma thickness by digital dermoscopy analysis: a retrospective study. Melanoma Res. 20, 212–217 (2010)
  9.Amouroux, M., Blondel, W.: Non-invasive determination of Breslow index. In: Cao, M.Y. (ed.) Current Management of Malignant Melanoma, pp. 29–44. InTech (2011)
  10.Stante, M., De Giorgi, V., Cappugi, P., Giannotti, B., Carli, P.: Non-invasive analysis of melanoma thickness by means of dermoscopy: a retrospective study. Melanoma Res. 11, 147–152 (2001)CrossRef
  11.Lens, M.B., Nathan, P., Bataille, V.: Excision margins for primary cutaneous melanoma: updated pooled analysis of randomized controlled trials. Arch. Surg. 142, 885–891 (2007)CrossRef
  12.Argenziano, G., Soyer, H., et al.: Interactive Atlas of Dermoscopy. EDRA-Medical Publishing and New Media, Milan (2000)
  13.Sáez, A., Serrano, C., Acha, B.: Model-based classification methods of global patterns in dermoscopic images. IEEE Trans. Med. Imaging 33, 1137–1147 (2014)CrossRef
  14.Sáez, A., Mendoza, C.S., Acha, B., Serrano, C.: Development and evaluation of perceptually adapted colour gradients. IET Image Proc. 7, 355–363 (2013)MathSciNet CrossRef
  15.Soyer, H., Argenziano, G., Hofmann-Wellenhof, R., Johr, R.: Color Atlas of Melanocytic Lesions of the Skin. Springer, Heidelberg (2010)
  16.Weismann, K., Lorentzen, H.F.: Dermoscopic color perspective. Arch. Dermatol. 142, 1250 (2006)CrossRef
  17.Seidenari, S., Pellacani, G., Grana, C.: Computer description of colours in dermoscopic melanocytic lesion images reproducing clinical assessment. Br. J. Dermatol. 149, 523–529 (2003)CrossRef
  18.Argenziano, G., Fabbrocini, G., Carli, P., De Giorgi, V., Delfino, M.: Clinical and dermatoscopic criteria for the preoperative evaluation of cutaneous melanoma thickness. J. Am. Acad. Dermatol. 40, 61–68 (1999)CrossRef
  19.Lorentzen, H., Weismann, K., Grønhøj Larsen, F.: Dermatoscopic prediction of melanoma thickness using latent trait analysis and likelihood ratios. Acta Derm. Venereol. 81, 38–41 (2001)CrossRef
  20.da Silva, V., Ikino, J., Sens, M., Nunes, D., Di Giunta, G.: Dermoscopic features of thin melanomas: a comparative study of melanoma in situ and invasive melanomas smaller than or equal to 1mm [características dermatoscópicas de melanomas finos: Estudo comparativo entre melanomas in situ e melanomas invasivos menores ou iguais a 1mm]. Anais Brasileiros de Dermatologia 88, 712–717 (2013)CrossRef
  21.Otsu, N.: Threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. SMC–9, 62–66 (1979). (cited By 10522)
  22.Sadeghi, M., Razmara, M., Lee, T., Atkins, M.: A novel method for detection of pigment network in dermoscopic images using graphs. Comput. Med. Imaging Graph. 35, 137–143 (2011)CrossRef
  23.Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC3, 610–621 (1973)CrossRef
  24.Landwehr, N., Hall, M., Frank, E.: Logistic model trees. Mach. Learn. 59, 161–205 (2005)CrossRef MATH
  25.Hervás-Martínez, C., Martínez-Estudillo, F.J., Carbonero-Ruz, M.: Multilogistic regression by means of evolutionary product-unit neural networks. Neural Netw. 21, 951–961 (2008)CrossRef MATH
  26.Hervás-Martínez, C., Martínez-Estudillo, F.: Logistic regression using covariates obtained by product-unit neural network models. Pattern Recogn. 40, 52–64 (2007)CrossRef MATH
  27.Gutiérrez, P.A., Hervás-Martínez, C., Martínez-Estudillo, F.J.: Logistic regression by means of evolutionary radial basis function neural networks. IEEE Trans. Neural Networks 22, 246–263 (2011)CrossRef
  28.Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011)CrossRef
  29.Chu, W., Keerthi, S.S.: Support vector ordinal regression. Neural Comput. 19, 792–815 (2007)MathSciNet CrossRef MATH
  30.Gutiérrez, P., Pérez-Ortiz, M., Sánchez-Monedero, J., Fernandez-Navarro, F., Hervás-Martínez, C.: Ordinal regression methods: survey and experimental study. IEEE Trans. Knowl. Data Eng. 28, 127–146 (2016)CrossRef
  31.Lin, H.T., Li, L.: Reduction from cost-sensitive ordinal ranking to weighted binary classification. Neural Comput. 24, 1329–1367 (2012)CrossRef MATH
  32.Sun, B.Y., Li, J., Wu, D.D., Zhang, X.M., Li, W.B.: Kernel discriminant learning for ordinal regression. IEEE Trans. Knowl. Data Eng. 22, 906–910 (2010)CrossRef
  33.Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. Spec. Interest Group Knowl. Discov. Data Min. Explorer Newsl. 11, 10–18 (2009)
  34.Fernández-Caballero, J.C., Martínez-Estudillo, F.J., Hervás-Martínez, C., Gutiérrez, P.A.: Sensitivity versus accuracy in multiclass problems using memetic pareto evolutionary neural networks. IEEE Trans. Neural Networks 21, 750–770 (2010)CrossRef
  35.Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: one-sided selection. In: Proceedings of the 14th International Conference on Machine Learning, pp. 179–186. Morgan Kaufmann (1997)
  36.Baccianella, S., Esuli, A., Sebastiani, F.: Evaluation measures for ordinal regression. In: Proceedings of the Ninth International Conference on Intelligent Systems Design and Applications (ISDA 2009), pp. 283–287. IEEE Computer Society, San Mateo, CA (2009)
  
• 作者单位：Javier Sánchez-Monedero (17)
  Aurora Sáez (18)
  María Pérez-Ortiz (17)
  Pedro Antonio Gutiérrez (19)
  Cesar Hervás-Martínez (19)
  
  17. Department of Quantitative Methods, Universidad Loyola Andalucía, Escritor Castilla Aguayo, 4, 14004, Córdoba, Spain
  18. Signal Theory and Communications Department, University of Seville, 41092, Seville, Spain
  19. Department of Computer Science and Numerical Analysis, Campus de Rabanales, Edificio Albert Einstein, University of Córdoba, 14071, Córdoba, Spain
  
• 丛书名：Hybrid Artificial Intelligent Systems
• ISBN：978-3-319-32034-2
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Melanoma is a type of cancer that occurs on the skin. Only in the US, 50,000–100,000 patients are yearly diagnosed with melanoma. Five year survival rate highly depends on early detection, varying between 99 % and 15 % depending on the melanoma stage. Melanoma is typically identified with a visual inspection and lately confirmed and classified by a biopsy. In this work, we propose a hybrid system combining features which describe melanoma images together with machine learning models that learn to distinguish melanoma lesions. Although previous works distinguish melanoma and non-melanoma images, those works focus only in the binary case. Opposed to this, we propose to consider finer classification levels within a five class learning problem. We evaluate the performance of several nominal and ordinal classifiers using four performance metrics to provide highlights of several aspects of classification performance, achieving promising results.