Advertisement

Mammographic Image Segmentation and Risk Classification Using a Novel Texture Signature Based Methodology

  • Wenda He
  • Erika R. E. Denton
  • Reyer Zwiggelaar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6136)

Abstract

Clinical research has shown that breast cancer risk is strongly related to characteristic mixture of breast tissues as seen on mammographic images. We present an automatic mammographic image segmentation approach, which uses a novel texture signature based methodology, the resultant segmentation can be found useful as a means of aiding radiologists’ estimation in mammographic risk assessment. The developed approach consists of four distinct steps: 1) feature extraction use a stack of small detail annotated mammographic patches, 2) Tabár mammographic building blocks are modelled as texture signatures, 3) model selection and reduction is used to remove noise and possible outliers, and 4) mammographic image segmentation. Visual assessment indicates good and consistent segmentation results. The MIAS database was used in a quantitative and qualitative evaluation with respect to mammographic risk assessment based on both Tabár and Birads risk categories. We found substantial agreement (κ= 0.7 and 0.75 based on Tabár and Birads risk categories, respectively) between classification results and ground truth data. Classification accuracy were 78% and 75% in Tabár and Birads categories, respectively; 86% and 87% in the corresponding low and high categories for Tabár and Birads, respectively.

Keywords

Tabár breast segmentation breast classification mammography parenchymal patterns 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Tabár, L., et al.: Breast Cancer: The Art And Science Of Early Detection With Mamography: Perception, Interpretation, Histopatholigic Correlation, 1st edn. Georg Thieme Verlag (2004)Google Scholar
  2. 2.
    Wolfe, J.N.: Risk for breast cancer development determind by mammographic parenchymal pattern. Cancer 37(5), 2486–2492 (1976)CrossRefGoogle Scholar
  3. 3.
    Guliato, D., et al.: Feature extraction from a signature based on the turning angle function for the classification of breast tumors. Journal of Digital Imaging 21, 129–144 (2008)CrossRefGoogle Scholar
  4. 4.
    Zwiggelaar, R., Taylor, C.J.: Abnormal masses in mammograms: Detection using scale-orientation signatures. In: Medical Image Computing and Computer-Assisted Intervention, London, UK, pp. 570–577. Springer, Heidelberg (1998)Google Scholar
  5. 5.
    Holmes, A.S., et al.: Transforming pixel signatures into an improved metric space. Image Vision Comput. 20(9-10), 701–707 (2002)CrossRefGoogle Scholar
  6. 6.
    Suckling, J., et al.: The mammographic images analysis society digital mammogram database. In: Dance, Gale, Astley, Gairns (eds.) Excerpta medica. International Congress Series, vol. 1069, pp. 375–378. Elsevier, Amsterdam (1994)Google Scholar
  7. 7.
    He, W., et al.: Mammographic segmentation based on mammographic parenchymal patterns and spatial moments. In: 9th International Conference on Information Technology and Applications in Biomedicine, p. 115 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Wenda He
    • 1
  • Erika R. E. Denton
    • 2
  • Reyer Zwiggelaar
    • 1
  1. 1.Department of Computer ScienceAberystwyth UniversityAberystwythUK
  2. 2.Department of RadiologyNorfolk & Norwich University HospitalNorwichUK

Personalised recommendations