Characterizing Breast Phenotype with a Novel Measure of Fibroglandular Structure

  • John H. Hipwell
  • Lewis D. Griffin
  • Patsy J. Whelehan
  • Wenlong Song
  • Xiying Zhang
  • Jan M. Lesniak
  • Sarah Vinnicombe
  • Andy Evans
  • Jonathan Berg
  • David J. Hawkes
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7361)

Abstract

Understanding, and accurately being able to predict, breast cancer risk would greatly enhance the early detection, and hence treatment, of the disease. In this paper we describe a new metric for mammographic structure, “orientated mammographic entropy”, via a comprehensive classification of image pixels into one of seven basic image feature (BIF) classes. These classes are flat (zero order), slope-like (first order), and maximum, minimum, light-lines, dark-lines and saddles (second order). By computing a reference breast orientation with respect to breast shape and nipple location, these classes are further subdivided into 23 orientated BIF classes. For a given mammogram a histogram is constructed from the proportion of pixels in each of the 23 classes, and the orientated mammographic entropy, H om , computed from this histogram. H om , shows good correlation between left and right breasts (r 2 = 0.76, N=478), and is independent of both mammographic breast area, a surrogate for breast size (r 2 = 0.07, N=974), and breast density, as estimated using Volpara TM software (r 2 = 0.11, N=385). We illustrate this metric by examining its relationship to familial breast cancer risk, for 118 subjects, using the BOADICEA genetic susceptibility to breast and ovarian cancer model.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    NHSBSP 61, Screening for Breast Cancer in England: Past and Future (February 2006) ISBN 1 84463 026 9, http://www.cancerscreening.nhs.uk/breastscreen/publications/nhsbsp61.pdf
  2. 2.
    Antoniou, A.C., Pharoah, P.P.D., Smith, P., Easton, D.F.: The boadicea model of genetic susceptibility to breast and ovarian cancer. British Journal of Cancer 91(8), 1580–1590 (2004)Google Scholar
  3. 3.
    Boehm, H.F., Schneider, T., Buhmann-Kirchhoff, S.M., Schlossbauer, T., Rjosk-Dendorfer, D., Britsch, S., Reiser, M.: Automated classification of breast parenchymal density: Topologic analysis of x-ray attenuation patterns depicted with digital mammography. American Journal of Roentgenology 191(6), W275–W282 (2008); Times Cited: 0Google Scholar
  4. 4.
    Boyd, N.F., Jensen, H.M., Cooke, G., Han, H.L.: Relationship Between Mammographic and Histological Risk- Factors For Breast-Cancer. J. National Cancer Institute 84, 1170–1179 (1992)CrossRefGoogle Scholar
  5. 5.
    Brandt, S.S., Karemore, G., Karssemeijer, N., Nielsen, M.: An anatomically oriented breast coordinate system for mammogram analysis. IEEE Transactions on Medical Imaging 30(10), 1841–1851 (2011)CrossRefGoogle Scholar
  6. 6.
    Crosier, M., Griffin, L.D.: Using basic image features for texture classification. International Journal of Computer Vision 88(3), 447–460 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Griffin, L.D.: The second order local-image-structure solid. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(8), 1355–1366 (2007)CrossRefGoogle Scholar
  8. 8.
    Jamal, N., Kg, K.H., Looi, L.M., McLean, D., Zulfiqar, A., Tan, S.P., Liew, W.F., Shantini, A., Ranganathan, S.: Quantitative assessment of breast density from digitized mammograms into tabar’s patterns. Physics in Medicine and Biology 51(22), 5843–5857 (2006)CrossRefGoogle Scholar
  9. 9.
    Li, H., Giger, M.L., Olopade, O.I., Lan, L.: Validation of Mammographic Texture Analysis for Assessment of Breast Cancer Risk. In: Martí, J., Oliver, A., Freixenet, J., Martí, R. (eds.) IWDM 2010. LNCS, vol. 6136, pp. 267–271. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Manduca, A., Carston, M.J., Heine, J.J., Scott, C.G., Pankratz, V.S., Brandt, K.R., Sellers, T.A., Vachon, C.M., Cerhan, J.R.: Texture Features from Mammographic Images and Risk of Breast Cancer. Cancer Epidemiology Biomarkers & Prevention 18, 837–845 (2009)CrossRefGoogle Scholar
  11. 11.
    McCormack, V.A., Silva, I.D.S.: Breast density and parenchymal patterns as markers of breast cancer risk: A meta-analysis. Cancer Epidemiology Biomarkers & Prevention 15(6), 1159–1169 (2006)CrossRefGoogle Scholar
  12. 12.
    Nielsen, M., Karemore, G., Loog, M., Raundahl, J., Karssemeijer, N., Otten, J.D.M., Karsdal, M.A., Vachon, C.M., Christiansen, C.: A novel and automatic mammographic texture resemblance marker is an independent risk factor for breast cancer. Cancer Epidemiology 35(4), 381–387 (2011)CrossRefGoogle Scholar
  13. 13.
    Raundahl, J., Loog, M., Pettersen, P., Tanko, L.B., Nielsen, M.: Automated effect-specific mammographic pattern measures. IEEE Transactions on Medical Imaging 27(8), 1054–1060 (2008)CrossRefGoogle Scholar
  14. 14.
    Reiser, I., Sidky, E.Y., Nishikawa, R.M., Pan, X.: Development of an Analytic Breast Phantom for Quantitative Comparison of Reconstruction Algorithms for Digital Breast Tomosynthesis. In: Astley, S.M., Brady, M., Rose, C., Zwiggelaar, R. (eds.) IWDM 2006. LNCS, vol. 4046, pp. 190–196. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  15. 15.
    Wolfe, J.N.: Breast patterns as an index of risk for developing breast-cancer. American Journal of Roentgenology 126(6), 1130–1139 (1976)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • John H. Hipwell
    • 1
  • Lewis D. Griffin
    • 2
  • Patsy J. Whelehan
    • 3
  • Wenlong Song
    • 1
  • Xiying Zhang
    • 1
  • Jan M. Lesniak
    • 5
  • Sarah Vinnicombe
    • 3
  • Andy Evans
    • 3
  • Jonathan Berg
    • 4
  • David J. Hawkes
    • 1
  1. 1.Center for Medical Image ComputingUCLLondonUK
  2. 2.Department of Computer ScienceUCLLondonUK
  3. 3.Dundee Cancer Centre, Ninewells HospitalUni. of DundeeUK
  4. 4.The Human Genetics Unit, Ninewells HospitalUni. of DundeeUK
  5. 5.Computer Vision LaboratoryETHZürichSwitzerland

Personalised recommendations