Segmentation of Skin Cancer Using External Force Filtering Snake Based on Wavelet Diffusion

  • Jinshan TangEmail author
  • Shengwen Guo


Segmentation of skin cancer is an important task for cancer quantitative analysis and therapy. Although a lot of work has been done in the past, it remains a challenge to segment skin cancer in dermoscopy images due to different factors, such as irregular and fuzzy lesion borders, high contrast spots, and hairs. In this chapter, we investigate active contour models or snakes for the segmentation of skin cancer. Our target is to develop an active contour model which is robust to noise and thus to remove the preprocessing step such as noise reduction before segmentation. Our basic idea is to smooth the external forces in deformable model directly using wavelet diffusion which incorporates the wavelet multiscale analysis and anisotropic diffusion. In the proposed algorithm, the above filtering technique is applied to smooth gradient vector flow (GVF) field so as to detect the lesion boundary of a skin cancer image. We compared the original GVF snake, the Gaussian filtering GVF snake, and the wavelet diffusion GVF snake. Experimental results and quantitative metric demonstrate that the wavelet diffusion GVF snake can improve the robustness and achieve the best performance in lesion segmentation.


Skin cancer Boundary detection Wavelet diffusion Snake 


  1. 1.
    American Cancer Society (2009) Cancer facts & figures 2009. American Cancer Society, AtlantaGoogle Scholar
  2. 2.
    Schmid-Saugeon P, Guillod J, Thiran J-P (2003) Towards a computer-aided diagnosis system for pigmented skin lesions. Comput Med Imaging Graph 27(1):65–78CrossRefGoogle Scholar
  3. 3.
    Ilea DE, Whelan PF (2006) Automatic segmentation of skin cancer images using adaptive color clustering. In: China-Ireland international conference on information and communications technologies (CIICT06), pp 348–351Google Scholar
  4. 4.
    Jailani R, Hashim H, Taib MN, Sulaiman S (2004) Border segmentation on digitized psoriasis skin lesion images. In: 2004 IEEE region 10 conference TENCON, vol 3, pp 596–599Google Scholar
  5. 5.
    Taouil K, Romdhane NB (2006) Automatic segmentation and classification of skin lesion images. In: The 2nd international conferences on distributed frameworks for multimedica applications, pp 1–12Google Scholar
  6. 6.
    Xu L, Jackowski M, Goshtasby A et al (1997) Segmentation of skin cancer images. Image Vis Comput 17:65–74CrossRefGoogle Scholar
  7. 7.
    Li X, Aldridge B, Ballerini L, Fisher R, Rees J (2009) Depth data improves skin lesion segmentation. Proceedings of the 12th international conference on medical image computing and computer-assisted intervention: part II, London, UK, pp 1100–1107Google Scholar
  8. 8.
    Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331CrossRefGoogle Scholar
  9. 9.
    Chung DH, Sapiro G (2000) Segmenting skin lesions with partial-differential-equations-based image processing algorithms. IEEE Trans Med Imaging 19(7):763–767PubMedCrossRefGoogle Scholar
  10. 10.
    Yuan X, Situ N, Zouridakis G (2009) A narrow band graph partitioning method for skin lesion segmentation. Pattern Recognit 42(6):1017–1028CrossRefGoogle Scholar
  11. 11.
    Tang J (2009) A multi-direction GVF snake for the segmentation of skin cancer images. Pattern Recognit 42(6):1172–1179CrossRefGoogle Scholar
  12. 12.
    Xu C, Prince JL (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359–369PubMedCrossRefGoogle Scholar
  13. 13.
    Whitaker RT, Prizer SM (1993) A multi scale approach to nonuniform diffusion. CVGIP: Image Underst 57(1):99–110CrossRefGoogle Scholar
  14. 14.
    Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639CrossRefGoogle Scholar
  15. 15.
    Yu Y, Acton ST (2002) Speckle reducing anisotropic diffusion. IEEE Trans Image Process 11(11):1260–1270PubMedCrossRefGoogle Scholar
  16. 16.
    Jin JS, Wang Y, Hiller J (2000) An adaptive nonlinear diffusion algorithm for filtering medical images. IEEE Trans Inf Technol Biomed 4(4):298–305PubMedCrossRefGoogle Scholar
  17. 17.
    Krissian K, Westin CF, Kikinis R, Vosburgh KG (2007) Oriented speckle reducing anisotropic diffusion. IEEE Trans Image Process 16(5):1412–1424PubMedCrossRefGoogle Scholar
  18. 18.
    Yue Y, Croitoru MM, Bidan A (2006) Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images. IEEE Trans Med Imaging 25(3):297–311PubMedCrossRefGoogle Scholar
  19. 19.
    Zong X, Laine AF, Geiser EA (1998) Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing. IEEE Trans Med Imaging 7(4):532–540CrossRefGoogle Scholar
  20. 20.
    Yue Y, Clark JW (2007) Speckle suppression for 3D ultrasound images using nonlinear multiscale wavelet diffusion. Medical Imaging 2007: Ultrasonic Imaging and Signal Processing. Edited by Emelianov, Stanislav Y.; McAleavey, Stephen A.. Proceedings of the SPIE, Volume 6513, pp. 65130Y (2007).Google Scholar
  21. 21.
    Weickert J (1998) Anisotropic diffusion in image processing. Teubner-Verlag, Stuttgart, GermanyGoogle Scholar
  22. 22.
    Shih ACC, Liao HYM, Lu CS (2003) A new iterated two-band diffusion equation: theory and its application. IEEE Trans Image Process 12(4):466–476PubMedCrossRefGoogle Scholar
  23. 23.
    Mallat S, Zhong S (1992) Characterization of signals from multiscale edges. IEEE Trans Pattern Anal Mach Intell 14(7):710–732CrossRefGoogle Scholar
  24. 24.
    Tang J, Sun Q (2009) A 3-D anisotropic diffusion filter for speckle reduction in 3-D ultrasound images. Proc SPIE 7239:72390T–72390T-9CrossRefGoogle Scholar
  25. 25.
    Pratt WK (1978) Digital image processing. John Wiley, New YorkGoogle Scholar
  26. 26.

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.Department of Advanced TechnologiesAlcorn State UniversityLormanUSA

Personalised recommendations