Advertisement

A Fully Automatic Random Walker Segmentation for Skin Lesions in a Supervised Setting

  • Paul Wighton
  • Maryam Sadeghi
  • Tim K. Lee
  • M. Stella Atkins
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5762)

Abstract

We present a method for automatically segmenting skin lesions by initializing the random walker algorithm with seed points whose properties, such as colour and texture, have been learnt via a training set. We leverage the speed and robustness of the random walker algorithm and augment it into a fully automatic method by using supervised statistical pattern recognition techniques. We validate our results by comparing the resulting segmentations to the manual segmentations of an expert over 120 cases, including 100 cases which are categorized as difficult (i.e.: low contrast, heavily occluded, etc.). We achieve an F-measure of 0.95 when segmenting easy cases, and an F-measure of 0.85 when segmenting difficult cases.

References

  1. 1.
    Braun, R.P., Rabinovitz, H.S., Oliviero, M., Kopf, A.W., Saurat, J.H.: Can automated dermoscopy image analysis instruments provide added benefit for the dermatologist? British Journal of Dermatology 157(5), 926–933 (2007)CrossRefGoogle Scholar
  2. 2.
    Grady, L.: Random walks for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(11), 1768–1783 (2006)CrossRefGoogle Scholar
  3. 3.
    Celebi, M., Aslandogan, et al.: Unsupervised border detection in dermoscopy images. Skin Research and Technology 13(4), 454–462 (2007)CrossRefGoogle Scholar
  4. 4.
    Fitzpatrick, J.M., Sonka, M.: Handbook of Medical Imaging, Volume 2. Medical Image Processing and Analysis (SPIE Press Monograph Vol. PM80). 1s edn. SPIE–The International Society for Optical Engineering (June 2000)Google Scholar
  5. 5.
    Celebi, M.E., Kingravi, H.A., Uddin, B., Iyatomi, H., Aslandogan, Y.A., Stoecker, W.V., Moss, R.H.: A methodological approach to the classification of dermoscopy images. Computerized Medical Imaging and Graphics, 362–373 (2007)Google Scholar
  6. 6.
    Grady, L., Schiwietz, T., Aharon, S., Munchen, T.U.: Random walks for interactive organ segmentation in two and three dimensions: Implementation and validation. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3750, pp. 773–780. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Argenziano, G., Soyer, H., et al.: Interactive Atlas of Dermoscopy (Book and CD-ROM). Edra medical publishing and new media (2000)Google Scholar
  8. 8.
    Soyer, H., Argenziano, G., et al.: Dermoscopy of Pigmented Skin Lesions. An Atlas based on the Consesnsus Net Meeting on Dermoscopy. Edra medical publishing and new media (2000)Google Scholar
  9. 9.
    Huang, Z., Chau, K.: A new image thresholding method based on Gaussian mixture model. Applied Mathematics and Computation 205(2), 899–907 (2008)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1), 62–66 (1979)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Makhoul, J., Kubala, F., Schwartz, R., Weischedel, R.: Performance measures for information extraction. In: Broadcast News Workshop 1999, p. 249 (1999)Google Scholar
  12. 12.
    Hance, G., Umbaugh, S., Moss, R., Stoecker, W.: Unsupervised color image segmentation: with application to skin tumor borders. IEEE Engineering in Medicine and Biology Magazine 15(1), 104–111 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Paul Wighton
    • 1
    • 2
    • 3
  • Maryam Sadeghi
    • 1
    • 3
  • Tim K. Lee
    • 1
    • 2
    • 3
  • M. Stella Atkins
    • 1
  1. 1.School of Computing ScienceSimon Fraser UniversityCanada
  2. 2.Department of Dermatology and Skin ScienceUniversity of British Columbia and Vancouver Coastal Health Research InstituteCanada
  3. 3.Cancer Control Research Program and Cancer Imaging DepartmentBC Cancer Research CentreCanada

Personalised recommendations