Color Segmentation of Breast Thermograms: A Comparative Study

Chapter
First Online:
Part of the Series in BioEngineering book series (SERBIOENG)

Abstract

Color segmentation of breast thermograms can have a crucial performance in tumor detection. There is a relation between blood vessel activity and the surrounding area temperature . Once a cancer increases blood vessel activity, the cancer cells and their surrounding tissue become hotter than normal tissue. Pre-cancer and cancer cells need plenty of nutrients to multiply and survive consequently; they are highly metabolic tissue and have different thermal patterns compared to the normal one. In this paper, a comparison work is presented for three modeled color segmentation approaches: K-means, mean shift (MS), and fuzzy c-means (FCM) applied to infrared breast images. There are some drawbacks for K-means and MS approaches. Almost empty clusters may be obtained in the segmentation results using K-means algorithm. In addition, we frequently confront almost empty clusters with MS algorithm due to its sensitiveness to the window size parameter. Choosing an appropriate window size parameter is not an easy task. On the other hand, the fuzzy inherent breast thermal images aid the FCM technique to obtain more precise outcomes. Malignant tumors show hotter thermal patterns than healthy tissues and even with benign tissues. Segmenting different parts of two breasts in terms of their temperature has potential helping to identify abnormal breast tissues.

Keywords

Breast Cancer detection Thermogram Pseudo-coloring Color segmentation K-means Fuzzy c-means Mean shift 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Etehadtavakol, M., Chandran, V., Ng, E.Y.K., Kafieh, R.: Breast cancer detection from thermal images using bispectral invariant features. Int. J. Thermal Sci. 69, 21–36 (2013)CrossRefGoogle Scholar
  2. 2.
    Jones, B.F.: A reappraisal of the use of infrared thermal image analysis in medicine. IEEE Trans. Med. Imaging 17(6), 1019–1027 (1998). doi: 10.1109/42.746635 CrossRefGoogle Scholar
  3. 3.
    Ng, E.Y.K.: A review of thermography as promising non- invasive detection modality for breast tumour. Int. J. Therm. Sci. 48(5), 849–859 (2009)CrossRefGoogle Scholar
  4. 4.
    Diakides, N., Bronzino, J.D.: Medical Infrared Imaging, 3rd edn. CRC, Taylor & Francis, New York (2008)Google Scholar
  5. 5.
    Ng, E.Y.K., Kee, E.C.: Advanced integrated technique in breast cancer thermography. J. Med. Eng. Technol. 32(2), 103–114 (2008). doi: 10.1080/03091900600562040
  6. 6.
    Etehadtavakol, M., Ng E.Y.K., Breast thermography as a potential non-contact method in early detection of cancer: a review. J. Mech. Med. Biol. 13(2), 1330001-1–1330001-20 (2013)Google Scholar
  7. 7.
    Lawson, R.N.: Implications of surface temperature in the diagnosis of breast cancer. Can. Med. Assoc. J. 75, 4309–4310 (1956)Google Scholar
  8. 8.
    Vaughn G., “Image Processing Class Notes”, Texas Tech University Interdisciplinary Engineering Masters Program, 2007Google Scholar
  9. 9.
    Weeks, A.R., Fundamentals of Electronic Image Processing, 3rd edn. SPIE Press, Bellingham, Washington (2004)Google Scholar
  10. 10.
    Zhou, X., Zhang, C.: A perceptive uniform pseudo-color coding method of SAR images, Radar, CIE. International Conference, Oct. 2006 IEEE, pp. 1–4 (2006)Google Scholar
  11. 11.
  12. 12.
    Li, H., Burgess, A.E., Evaluation of signal detection performance with pseudo-color display and lumpy backgrounds, JrnlID 10916_ArtID 9213_Proof# 1 - 08/09/2008. In: Kundel, H.L. (ed.) SPIE, Medical Imaging: Image Perception, vol. 3036, pp. 143–149. Newport Beach CA, USA (1997)Google Scholar
  13. 13.
    Connolly, C., Fliess, T.: A study of efficiency and accuracy in the transformation from RGB to CIELAB color space. IEEE Trans. Image Process. 6, 1046–1048 (1997). doi: 10.1109/83.597279 CrossRefGoogle Scholar
  14. 14.
    Fukunaga, K., Hostetler, L.D.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 2, 32–40 (1975)Google Scholar
  15. 15.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)Google Scholar
  16. 16.
    Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17(8), 790–799 (1995)Google Scholar
  17. 17.
    Jin, H., Tao, W., Zhang, Y.: Color image segmentation based on mean shift and normalized cuts. IEEE Trans. Syst. Man Cyberetics 37(5), 1382–1389 (2007)Google Scholar
  18. 18.
    Mayer, A., Greenspan, H., Segmentation of brain MRI by adaptive mean shift, biomedical imaging: nano to micro 3rd IEEE International Symposium, pp. 319–322 (2006)Google Scholar
  19. 19.
    MacQueen, J.B., Some methods for classification and analysis of multivariate observations. In: Proceedings of Fifth Berkeley Symposium on Mathematical Statistical and Probability, vol. 1, pp. 281–297. University of California Press (1967)Google Scholar
  20. 20.
    Bezdek, J.C., Keller, J., Krisnapuram, R., Pal, N.R.: Fuzzy models and algorithms for pattern recognition and image processing. Kluwer, Norwell, MA (1999)Google Scholar
  21. 21.
    Forgy, E.W.: Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometrics 21, 768–769 (1965)Google Scholar
  22. 22.
    Etehadtavakol, M., Sadri, S, Ng, E.Y.K., Application of K- and fuzzy c-means for color segmentation of thermal infrared breast images. J. Med. Syst. 34(1), 35–42 (2010). doi: 10.1007/s10916-008-9213-1
  23. 23.
    AAT: http://aathermography.com. Access Aug 2015
  24. 24.
  25. 25.
  26. 26.
  27. 27.
    ST Imaging: http://www.stimaging.com.au/page2. Access Aug 2015
  28. 28.
    Deelers, S., Auwatanamongkol, S.: Enhancing K-means algorithm with initial cluster centers derived from data partitioning along the data axis with the highest variance. Int. J. Comput. Sci. 2, 4247–4252 (2007)Google Scholar
  29. 29.
    Bradley, P.S., Fayyad, U.M., Refining initial points for K-Means clustering. In: Proceedings of 15th International Conference on Machine Learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp. 91–99 (1998)Google Scholar
  30. 30.
    Krishna, K., Narasimha, M., Genetic K-Means algorithm. IEEE Trans. Syst. Man Cybern. 29(3), 433–439 (1999). doi: 10.1109/3477.764879
  31. 31.
    Golestani, N., EtehadTavakol, M., Ng, E.Y.K.: Level set method for segmentation of infrared breast thermograms. Exp. Clin. Sci. 13, 241–251 (2014)Google Scholar
  32. 32.
    Sowmya, B., Bhattacharya, S., Color image segmentation using fuzzy clustering techniques. IEEE Indicon, Conference, Chennai, India, pp: 41–45, Dec (2005)Google Scholar
  33. 33.
    Solvenia, K. R., Fuzzy C-means clustering and facility location problems. In: Proceeding of Artificial Intelligence and Soft Computing, Palma de Mallorca, Spain, p. 544 (2006)Google Scholar
  34. 34.
    Acharya, U.R., Ng, E.Y.K., Tan, J.H., et al.: An integrated index for the identification of diabetic retinopathy stages using texture parameters. J. Med. Syst. 36(3), 2011–2020 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.Isfahan University of Medical SciencesIsfahanIran
  2. 2.School of Mechanical and Aerospace Engineering, College of EngineeringNanyang Technological UniversitySingaporeSingapore

Personalised recommendations