Advertisement

Temporal Analysis of Mammograms Based on Graph Matching

  • Fei Ma
  • Mariusz Bajger
  • Murk J. Bottema
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5116)

Abstract

A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.

Keywords

temporal analysis mammogram registration graph matching computer-aided mammography 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jolion, J.M., Montanvert, A.: The adaptive pyramid: A framework for 2d image analysis. CVGIP: Image Understanding 55(3), 339–348 (1992)MATHCrossRefGoogle Scholar
  2. 2.
    Kok-Wiles, S.L., Brady, M., Hignam, R.: Comparing mammogram pairs for the detection of lesions. In: Proc. IWDM 1998, pp. 103–110 (1998)Google Scholar
  3. 3.
    Krissinel, E.B., Henrick, K.: Common subgraph isomorphism detection by backtracking search. Softw. Pract. Exper. 34, 591–607 (2004)CrossRefGoogle Scholar
  4. 4.
    Ma, F., Bajger, M., Bottema, M.J.: Robustness of two methods for segmenting salient features in screening mammograms. In: Digital Image Computing Techniques and Applications (DICTA 2007), 9th Biennial Conference of the Australian Pattern Recognition Society, December 2007, pp. 112–117 (2007)Google Scholar
  5. 5.
    Ma, F., Bajger, M., Slavotinek, J.P., Bottema, M.J.: Two graph theory based methods for identifying the pectoral muscle in mammograms. Pattern Recognition 40, 2592–2602 (2007)MATHCrossRefGoogle Scholar
  6. 6.
    Marias, K., Behrenbruch, C., Parbhoo, S., Seifalian, A., Brady, M.: A registration framework for the comparison of mammogram sequences. IEEE Trans. Med. Imag. 24(6), 782–790 (2005)CrossRefGoogle Scholar
  7. 7.
    Miyajima, K., Ralescu, A.: Spatial organization in 2d segmented images: Representation and recognition of primitive spatial relations. Fuzzy Sets and Systems 65(2-3), 225–236 (1994)CrossRefGoogle Scholar
  8. 8.
    Sallam, M., Bowyer, K.W.: Registration and difference analysis of corresponding mammogram images. Medical image analysis 3(2), 103–118 (1999)CrossRefGoogle Scholar
  9. 9.
    Tanimoto, S., Pavlidis, T.: A hierarchical data structure for picture processing. Comput. Graphics Image Process 4(2), 104–119 (1975)CrossRefGoogle Scholar
  10. 10.
    Timp, S., Karssemeijer, N.: Interval change analysis to improve computer aided detection in mammography. Medical Image Analysis 10(1), 82–95 (2006)CrossRefGoogle Scholar
  11. 11.
    Timp, S., Varela, C., Karssemeijer, N.: Temporal change analysis for characterization of mass lesions in mammography. IEEE Trans. Med. Imag. 26(7), 945–953 (2007)CrossRefGoogle Scholar
  12. 12.
    Ullmann, J.R.: An algorithm for subgraph isomorphism. Journal of the ACM 1(23), 31–42 (1976)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Fei Ma
    • 1
  • Mariusz Bajger
    • 1
  • Murk J. Bottema
    • 1
  1. 1.School of Computer Science, Engineering and MathematicsFlinders UniversityAdelaide SAAustralia

Personalised recommendations