Dermoscopy Image Processing for Chinese

Part of the Series in BioEngineering book series (SERBIOENG)


Dermoscopy image analysis technology is discussed based on Chinese in this chapter. It includes four aspects: preprocessing, segmentation, feature extraction and classification. Firstly, in preprocessing stage, hair is extracted out according to the elongate of connected region, and then removed from the image by using PDE-based image inpainting technology. Secondly, a novel dermoscopy image segmentation algorithm is introduced using self-generating neural network (SGNN) combined with genetic algorithm (GA). And in the feature description stage, the features including color, texture, shape and border are extracted for the lesion object. Lastly, the model of combined neural network classifier is employed to classify the lesion object successfully with a sensitivity and specificity of 93.3 and 96.7 % respectively. Based on the image analysis method disscussed in this chapter, an automatic analysis system of dermoscopy images of Chinese is successfully developed and has been applied for the clinical diagnosis of skin tumors.


hair removal PDE-based inpainting automatic segmentation  self-generating neural network feature extraction lesion object classification combined neural network classifier 


  1. 1.
    Siegel, R., Ward, E., Brawley, O., Jemal, A.: Cancer statistics. CA Cancer J. Clin. 61(4), 212–236 (2011)CrossRefGoogle Scholar
  2. 2.
    Korotkov, K., Garcia, R.: Computerized analysis of pigmented skin lesions: a review. Artif. Intell. Med. 56(2), 69–90 (2012)CrossRefGoogle Scholar
  3. 3.
    Celebi, M.E., Stoecker, W.V., Moss, R.H.: advances in skin cancer image analysis. Comput. Med. Imaging Graph. 35(2), 83–84 (2011)CrossRefGoogle Scholar
  4. 4.
    Andreassi, L., Pemtti, R., Burroni, M.: Computerized image analysis of pigmented lesions. Chronica Dermatol 1, 11–24 (1995)Google Scholar
  5. 5.
    Slue, W., Kopf, A.W., Rivers, J.K.: Total body photographs of dysplastic nevi. Archives of Dermatology 124, 1239–1243 (1988)CrossRefGoogle Scholar
  6. 6.
    Lee, T.K., Ng, V., Gallagher, R., et al.: Dullrazor: a software approach to hair removal from images. Comput. Biol. Med. 27(6), 533–543 (1997)CrossRefGoogle Scholar
  7. 7.
    Wighton, P., Lee, T.K., AtkinsaM.S.: Dermoscopic hair disocclusion using inpainting. In: Proceedings of the SPIE medical imaging, vol. 6914, pp. 691427–691427-8 (2008)Google Scholar
  8. 8.
    Zhou, H., Chen, M., Gass, R., Rehg, J.M., Ferris, L., Ho J., et al.: Feature-preserving artifact removal from dermoscopy images. In: Proceedings of the SPIE medical imaging, vol. 6914, pp. 69141B–69141B-9 (2008)Google Scholar
  9. 9.
    Kiani, K., Sharafat, A.R., Shaver, E., etal.: An improved dullrazor for digitally removing dark and light-colored hairs in dermoscopic images. Comput. Biol. Med. 41(3), 139–145 (2011)Google Scholar
  10. 10.
    Abbas, Q., Celebi, M.E., Garcia, I.F.: Hair removal methods: a comparative study for dermoscopy images. Biomed. Signal Process. Control 6(4), 395–404 (2011)CrossRefGoogle Scholar
  11. 11.
    Abbas, Q., Garcia, I.F., Celebi, M.E., Ahmad, W.: A feature-preserving hair removal algorithm for dermoscopy images. Skin Res. Techhnol. 19(1), e27–e36 (2013)CrossRefGoogle Scholar
  12. 12.
    Xie, F.Y., Qin, S.Y., Jiang, Z.G., Meng, R.S.: PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma. Comput. Med. Imaging Graph. 33(4), 275–282 (2009)CrossRefGoogle Scholar
  13. 13.
    Zeng, M., Li, J.X.: Optimized design of morphological improved top-hat filter based on improved genetic algorithms. Acta Optica Sinica 26(4), 510–515 (2006)Google Scholar
  14. 14.
    Soille, P.: Morphological Image Analysis: Principles and Applications, Springer, Berlin (1999)Google Scholar
  15. 15.
    Cui, Y.: Mathematics morphological algorithms and its application. Science Press, Beijing, China (2000)Google Scholar
  16. 16.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)CrossRefGoogle Scholar
  17. 17.
    Celebi, M.E., Kingravi, H., Iyatomi, H., Aslandogan, A., Stoecker, W.V., Moss, R.H.: Border detection in dermoscopy images using statistical region merging. Skin Res. and Technol. 14(3), 347–353 (2008)CrossRefGoogle Scholar
  18. 18.
    Celebi, M.E., Iyatomi, H., Schaefer, G., Stoecker, W.V.: Lesion border detection in dermoscopy images. Comput. Med. Imaging Graph. 33(2), 148–153 (2009)CrossRefGoogle Scholar
  19. 19.
    Grana, C., Pellacani, G., Cucchiara, R., Seidenari, S.: A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions. IEEE Trans. Med. Imaging 22(8), 959–964 (2003)CrossRefGoogle Scholar
  20. 20.
    Rubegni, P., Ferrari, A., Cevenini, G., Piccolo, D., Burron, M., et al.: Differentiation between pigmented spitz naevus and melanoma by digital dermoscopy and stepwise logistic discriminant analysis. Melanoma Res. 11(1), 37–44 (2011)CrossRefGoogle Scholar
  21. 21.
    Zhou, H., Schaefer, G., Celebi, M.E., Lin, F., Liu, T.: Gradient Vector Flow with Mean Shift for Skin Lesion Segmentation. Comput. Med. Imaging Graph. 35(2), 121–127 (2011)CrossRefGoogle Scholar
  22. 22.
    Celebi, M.E., Aslandogan, A., Stoecker, W.V.: Unsupervised border detection in dermoscopy images. Skin Res. Technol. 13(4), 454–462 (2007)CrossRefGoogle Scholar
  23. 23.
    Zhou, H., Schaefer, G., Sadka, A.H., Celebi, M.E.: Anisotropic mean shift based fuzzy c-means segmentation of dermoscopy images. IEEE J. Sel. Top. Sign. Proces. 3(1), 26–34 (2009)Google Scholar
  24. 24.
    Gao, J., Zhang, J., Fleming, M.G.: A novel multiresolution color image segmentation technique and its application to dermatoscopic image segmentation. In: Proceeding of IEEE International Conference on Image Process, Vancouver, BC, Canada (2000)Google Scholar
  25. 25.
    Cucchiara, R., Grana, C., Seidenari, S., Pellacani, G.: Exploiting color and topological features for region segmentation with recursive fuzzy C-means. Machine Graphics Vision 11(2/3), 169–182 (2002)Google Scholar
  26. 26.
    Xie, F., Bovik, Al.: Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Pattern Recognit. 46(3), 1012–1019 (2013)Google Scholar
  27. 27.
    Wen, W.X., Jennings, A., Liu, H.: Learning a neural tree. In: Proceeding of International Joint Conference on Neural Networks, vol. 2, pp. 751–756, Beijing, China (1992)Google Scholar
  28. 28.
    Inoue, H., Narihisa, H.: Efficiency of self-generating neural networks applied to pattern recognition. Math. Comput. Model. 38(11–13), 1225–1232 (2003)MathSciNetCrossRefMATHGoogle Scholar
  29. 29.
    Feng, S., Chaudhari, N.S.: A chaotic behavior decision algorithm based on self-generating neural network for computer games. In: Proceedings of IEEE Conference on 3rd Industrial Electronics and Applications, pp. 1912–1915, Singapore (2008)Google Scholar
  30. 30.
    Inoue, H., Narihisa, H.: Efficient pruning method for ensemble self-generating nerual networks. J. Syst. Cybern. Inf. 1(6), 72–77 (2003)Google Scholar
  31. 31.
    Mukhopadhyay, A., Bandyopadhyay, S., Maulik U.l.: Clustering using Multi-objective genetic algorithm and its application to image segmentation. In: Proceeding of IEEE International Conference on Systems, Man, and Cybernetics, vol. 10, pp. 2678–2683 (2006)Google Scholar
  32. 32.
    Zhu, Y., Jiang, L.J.: Image Segmentation Based on GA-FCM Clustering and Probability Relaxation. Laser Infrared 38(4), 292–295 (2008)Google Scholar
  33. 33.
    Awad, M., Chehdi, K., Nasri, A.: Multicomponent image segmentation using a genetic algorithm and artificial neural network. IEEE Geosci. Remote Sens. Lett. 4(4), 571–575 (2007)CrossRefGoogle Scholar
  34. 34.
    Hall, L.O., Ozyurt, I.B., Bezdek, J.C.: Clustering with a genetically optimized approach. IEEE Trans. Evolut Ccmput. 3(2), 103–112 (1999)CrossRefGoogle Scholar
  35. 35.
    Maulik, U., Bandyopadhyay, S.: Genetic algorithm based clustering technique. Pattern Recogn. 33, 1455–1465 (2000)CrossRefGoogle Scholar
  36. 36.
    Maulik, U., Bandyopadhyay, S.: Fuzzy partitioning using a real-coded variable-length genetic algorithm for pixel classification. IEEE Trans. Geosci. Remote Sens. 41(5), 1075–1081 (2003)CrossRefGoogle Scholar
  37. 37.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. B Cybern. 9(1), 62–66 (1979)MathSciNetCrossRefGoogle Scholar
  38. 38.
    Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. 1, 224–227 (1979)CrossRefGoogle Scholar
  39. 39.
    Dunn, J.C.: Well separated clusters and optimal fuzzy partitions. J. Cybern. 4, 95–104 (1974)MathSciNetCrossRefGoogle Scholar
  40. 40.
    Halkidi, M., Vazirgiannis, M., Batistakis, Y.: Quality scheme assessment in the clustering process. In: Procedding of European Conference on Principles and Practice of Knowledge Discovery in Databases, pp. 265–276, Lyon, France (2000)Google Scholar
  41. 41.
    Tanaka, T., Yamada, R., Tanaka, M., et al.: A study on the image diagnosis of melanoma. Proceedings of the 26th Annual International Conference of the IEEE EMBS, vol. 9, pp. 1597–1600 (2004)Google Scholar
  42. 42.
    Motoyarna, H., Tanaka, T., Tanka, M., et al.: Feature of malignant melanoma based on color information. SICE Annual Conf. Sapporo 1, 230–233 (2004)Google Scholar
  43. 43.
    Sachin, V., Atam, P.: Multi-spectral imaging and analysis for classification of melanoma. In: Proceedings of the 26th Annual International Conference of the IEEE EMBS vol. 9, pp. 503–506 (2004)Google Scholar
  44. 44.
    Celebi, M.E., Kingravi, H.A., Uddin, B., et al.: A methodological approach to the classification of dermoscopy images. Comput. Med. Imaging Graph. 31, 362–373 (2007)CrossRefGoogle Scholar
  45. 45.
    Abbas, Q., Celebi, M.E., Serrano, C., García, I.F.: Pattern classification of dermoscopy images: A perceptually uniform model. Pattern recogn. 46(1), 86–97 (2013)CrossRefGoogle Scholar
  46. 46.
    Ganster, H., Pinz, A., Rohrer, R., et al.: Automated melanoma recognition. IEEE Trans. Med. Imaging 20(3), 233–239 (2001)CrossRefGoogle Scholar
  47. 47.
    Hintz-Madsen M., Hansen L. K., Larsen J., et al. A probabilistic neural network framework for detection of malignant melanoma. In: Naguib RNG, Sherbet GV(ed) Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management, CRC Press, Boca Raton, 141–183 (2001)Google Scholar
  48. 48.
    Rubegni, P., Burroni, M., Cevenini, G., et al.: Digital dermoscopy. Analysis and artificial neural network for the differentiation of clinically atypical pigmented skin lesions: A retrospective study. J. Invest. Dermatol. 119(2), 471–474 (2002)CrossRefGoogle Scholar
  49. 49.
    Sboner, A., Eccher, C., Blanzieri, E., et al.: A multiple classifier system for early melanoma diagnosis. Artif. Intell. Med. 27(1), 29–44 (2003)CrossRefGoogle Scholar
  50. 50.
    Blum, A., Luedtke, H., Ellwanger, U., et al.: Digital image analysis for diagnosis of cutaneous melanoma development of a highly effective computer algorithm based on analysis of 837 melanocytic lesions. Br. J. Dermatol. 151(5), 1029–1038 (2004)CrossRefGoogle Scholar
  51. 51.
    Menzies, S.W., Bischof, L., Talbot, H., et al.: The performance of SolarScan: An automated dermoscopy image analysis instrument for the diagnosis of primary melanoma. Arch. Dermatol. 141(11), 1388–1396 (2005)CrossRefGoogle Scholar
  52. 52.
    Capdehourat, G., Corez, A., Bazzano, A., et al.: pigmented skin lesions classification using dermatoscopic images. Progress Pattern Recognition, Image Analysis, Computer Vision, Applications 5856(11), 537–544 (2009)CrossRefGoogle Scholar
  53. 53.
    Stolz, W., Riemann, A., Cognetta, A.B., et al.: ABCD rules of dermatoscopy: a new practical method for early recognition of malignant melanoma. Eur. J. Dermatol. 4(7), 521–527 (1994)Google Scholar
  54. 54.
    Menzies, S., Crook, B., McCarthy, W., et al.: Automated instrumentation and diagnosis of invasive melanoma. Melanoma Res. 7(Suppl. 1), s13 (1997)CrossRefGoogle Scholar
  55. 55.
    McGovern, T.W., Litaker, M.S.: Clinical predictors of malignant pigmented lesions: a comparson of the Glasgow seven-point checklist and the American Cancer Society’s ABCDs of pigmented lesions. J. Dermatol. Surg. Onc 18, 22–26 (1992)CrossRefGoogle Scholar
  56. 56.
    Celebi, M.E., Kingravi, H.A., Uddin, B., et al.: A methodological approach to the classification of dermoscopy images. Comput. Med. Imaging Graph. 31, 362–373 (2007)CrossRefGoogle Scholar
  57. 57.
    Fengying Xie. (2009) Segmentation and Classification of Dermoscopy Images Based on Computational dissertation at Beihang University in China.Google Scholar
  58. 58.
    Clausi, D.A.: An analysis of co-occurrence texture statistics as a function of gray level quantization. Can. J. Remote Sens. 28(1), 45–62 (2002)CrossRefGoogle Scholar
  59. 59.
    Andrew, A.M.: Another Efficient Algorithm for Convex Hulls in Two Dimensions. Inf. Process. Lett. 9(5), 216–219 (1979)CrossRefMATHGoogle Scholar
  60. 60.
    Hansen, L.K., Salamon, P.: Neural network ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 12(10), 993–1001 (1990)CrossRefGoogle Scholar
  61. 61.
    Hashem, S., Schmeiser, B., Yih Y.:Optimal linear combinations of neural networks: An Overview. In: IEEE International Conference on Neyral Networks pp. 93–19 (1994)Google Scholar
  62. 62.
    Freund, Y., Schapire, R.E.: A Decision-TheoreticGeneralization of On-Line Learning and an Application to Boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)MathSciNetCrossRefMATHGoogle Scholar
  63. 63.
    Shen, Z.Q., Kong, F.S.: Optimizing weights by genetic algorithm for neural network ensemble. Lect. Notes Comput. Sci. 323–331 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Fengying Xie
    • 1
  • Yefen Wu
    • 1
  • Zhiguo Jiang
    • 1
  • Rusong Meng
    • 2
  1. 1.School of astronauticsBeihang UniversityBeijingChina
  2. 2.Department of DermatologyGeneral Hospital of the Air Force of the Chinese People’s Liberation ArmyBeijingChina

Personalised recommendations