Image Similarity and Asymmetry to Improve Computer-Aided Detection of Breast Cancer

  • Dave Tahmoush
  • Hanan Samet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4046)


An improved image similarity method is introduced to recognize breast cancer, and it is incorporated into a computer-aided breast cancer detection system through Bayes Theorem. Radiologists can use the differences between the left and right breasts, or asymmetry, in mammograms to help detect certain malignant breast cancers. Image similarity is used to determine asymmetry using a contextual and then a spatial comparison. The mammograms are filtered to find the most contextually significant points, and then the resulting point set is analyzed for spatial similarity. We develop the analysis through a combination of modeling and supervised learning of model parameters. This process correctly classifies mammograms 84% of the time, and significantly improves the accuracy of a computer-aided breast cancer detection system by 71%.


Breast Cancer Image Retrieval Image Similarity Digital Mammography Digital Mammogram 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    American Cancer Society. Breast Cancer Facts and Figures 1999-2000. American Cancer Society, Inc., Atlanta, GA (1999)Google Scholar
  2. 2.
    Linda, J., Burhenne, W., Wood, S.A., D’Orsi, C.J., Feig, S.A., Kopans, D.B., O’Shaughnessy, K.F., Sickles, E.A., Tabar, L., Vyborny, C.J., Castellino, R.A.: Potential contribution of computer-aided detection to the sensitivity of screening mammography. Radiology 215, 554–562 (2000)Google Scholar
  3. 3.
    Freer, T.W., Ulissey, M.J.: Screening mammography with computer- aided detection. Radiology 220, 781–786 (2001)CrossRefGoogle Scholar
  4. 4.
    Ferrari, R.J., Rangayyan, R.M., Desautels, J.E.L., Frere, A.F.: Analysis of asymmetry in mammograms via directional filtering with Gabor wavelets. IEEE Trans. on Medical Imaging 20(9) (2001)Google Scholar
  5. 5.
    Astley, S., Mistry, T., Boggis, C.R.M., Hillier, V.F.: Should we use humans or a machine to pre-screen mammograms? In: Proc. of the Sixth Int. Workshop on Digital Mammography, pp. 476–480 (2002)Google Scholar
  6. 6.
    Astley, S., Gilbert, F.J.: Computer-aided detection in mammography. Clinical Radiology 59, 390–399 (2004)CrossRefGoogle Scholar
  7. 7.
    Tahmoush, D.A., Samet, H.: Using image similarity and asymmetry to detect breast cancer. In: Proc. SPIE Int. Soc. Opt. Eng., vol. 6144 (2006)Google Scholar
  8. 8.
    Soffer, A., Samet, H.: Pictorial queries by image similarity. In: Proc. of the 13th Int. Conf. on Pattern Recognition, vol. 3, pp. 114–119 (1996)Google Scholar
  9. 9.
    Gudivada, V., Raghavan, V.: Design and evaluation of algorithms for image retrieval by spatial similarity. ACM Trans. on Inf. Sys. 13(2), 115–144 (1995)CrossRefGoogle Scholar
  10. 10.
    El-Naqa, I., Yang, Y., Galatsanos, N.P., Nishikawa, R.M., Wernick, M.N.: A similarity learning approach to content based image retrieval: application to digital mammography. IEEE Trans. on Medical Imaging 23(10), 1233–1244 (2004)CrossRefGoogle Scholar
  11. 11.
    Goldberger, J., Gordon, S., Greenspan, H.: An efficient image similarity measure based on approximations of kl-divergence between two gaussian mixtures. In: Proc. of the Ninth IEEE Int. Conf. on Computer Vision, pp. 487–493 (2003)Google Scholar
  12. 12.
    Swett, H.A., Miller, P.L.: Icon: a computer-based approach to differential diagnosis in radiology. Radiology 163, 555–558 (1987)Google Scholar
  13. 13.
    Guimond, A., Subsol, G.: Automatic mri database exploration and applications. Pattern Recognition and Artificial Intelligence 11(8), 1345–1365 (1997)CrossRefGoogle Scholar
  14. 14.
    Heath, M.D., Bowyer, K.W.: Mass detection by relative image intensity. In: The Proc. of the 5th Int. Conf. on Digital Mammography, Medical Physics Publishing, Madison (2000)Google Scholar
  15. 15.
    Sajda, P., Spense, C., Parra, L.: Capturing contextual dependencies in medical imagery using hierarchical multi-scale models. In: Proc. of the IEEE Int. Symp. on Biomedical Imaging, pp. 165–168 (2002)Google Scholar
  16. 16.
    Kalman, B.L., Kwasny, S.C., Reinus, W.R.: Diagnostic screening of digital mammograms using wavelets and neural networks to extract structure. Technical Report 98-20, Washington University (1998)Google Scholar
  17. 17.
    Lui, S., Babbs, C.F., Delp, E.J.: Multiresolution detection of spiculated lesions in digital mammograms. IEEE Trans. on Image Processing 6, 874–884 (2001)Google Scholar
  18. 18.
    Campanini, R., Bazzani, A., Bevilacqua, A., Bollini, D., Dongiovanni, D., Iampieri, E., Lanconelli, N., Riccardi, A., Roffilli, M., Tazzoli, R.: A novel approach to mass detection in digital mammography based on support vector machines. In: Proc. of the 6th Int. Workshop on Digital Mammography (2002)Google Scholar
  19. 19.
    Miller, P., Astley, S.: Detection of breast asymmetry using anatomical features. In: Proc. of the Int. Society for Optical Engineering Conf. on Biomedical Image Processing and Biomedical Visualization, vol. 1905, pp. 433–442 (1993)Google Scholar
  20. 20.
    Wirth, M.A., Jennings, A.: A nonrigid-body approach to matching mammograms. In: Proc. of the IEEE Image Processing and its Applications, pp. 484–487 (1999)Google Scholar
  21. 21.
    Yin, F.F., Giger, M.L., Doi, K., Metz, C.E., Vyborny, C.J., Schmidt, R.A.: Computerized detection of masses in digital mammograms: analysis of bilateral subtraction images. Medical Physics 18, 955–963Google Scholar
  22. 22.
    Gondra, I., Heisterkamp, D.R.: Learning in region-based image retrieval with generalized support vector machines. In: Proc. of the Computer Vision and Pattern Recognition, p. 149 (2004)Google Scholar
  23. 23.
    Heath, M.D., Bowyer, K.W., Kopans, D., et al.: Current status of the digital database for screening mammography. In: Digital Mammography, pp. 457–460. Kluwer Academic Publishers, Dordrecht (1998)Google Scholar
  24. 24.
    Dettling, M., Buhlmann, P.: Boosting for tumor classification with gene expression data. Bioinformatics 19(9), 1061–1069 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Dave Tahmoush
    • 1
    • 2
  • Hanan Samet
    • 1
  1. 1.Computer Science Department, Center for Automation Research, Institute for Advanced Computer ScienceUniversity of MarylandCollege ParkUSA
  2. 2.Applied Physics LaboratoryJohns Hopkins UniversityLaurelUSA

Personalised recommendations