An Advanced Probabilistic Framework for Assisting Screening Mammogram Interpretation

  • Marina Velikova
  • Nivea Ferreira
  • Maurice Samulski
  • Peter J. F. Lucas
  • Nico Karssemeijer
Part of the Studies in Computational Intelligence book series (SCI, volume 309)

Abstract

Breast cancer is the most common form of cancer among women world-wide. One in nine women will be diagnosed with a form of breast cancer in her lifetime. In an effort to diagnose cancer at an early stage, screening programs have been introduced by using periodic mammographic examinations in asymptomatic women. In evaluating screening cases, radiologists are usually presented with two mammographic images of each breast as a cancerous lesion tends to be observed in different breast projections (views). Most computer-aided detection (CAD) systems, on the other hand, only analyse single views independently, and thus fail to account for the interaction between the views and the breast cancer detection can be obscured due to the lack of consistency in lesion marking. This limits the usability and the trust in the performance of such systems. In this chapter, we propose a unified Bayesian network framework for exploiting multi-view dependencies between the suspicious regions detected by a single-view CAD system. The framework is based on a multi-stage scheme, which models the way radiologists interpret mammograms, at four different levels: region, view, breast and case. At each level, we combine all available image information for the patient obtained from a single-view CAD system using a special class of Bayesian networks–causal independence models. The results from experiments with actual screening data of 1063 cases, from which 383 were cancerous, show that our approach outperforms the single-view CAD system in distinguishing between normal and abnormal cases. This is a promising step towards the development of automated systems that can provide a valuable “second opinion” to the screening radiologists for improved evaluation of breast cancer cases.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Otten, J.D., Broeders, M.J., Fracheboud, J., Otto, S.J., de Koning, H.J., Verbeek, A.L.: Impressive time-related influence of the Dutch screening programme on breast cancer incidence and mortality, 1975-2006. International Journal of Cancer 123(8), 1929–1934 (2008)CrossRefGoogle Scholar
  2. 2.
    Engeland, S.V.: Detection of mass lesions in mammograms by using multiple views. PhD Thesis (2006)Google Scholar
  3. 3.
    BI-RADS: Breast Imaging Reporting and Data System. American College of Radiology, Reston (1993)Google Scholar
  4. 4.
    Morton, M.J., Whaley, D.H., Brandt, K.R., Amrami, K.K.: Screening mammograms: interpretation with computer-aided detection-prospective evaluation. Radiology 239, 375–383 (2006)CrossRefGoogle Scholar
  5. 5.
    Sardo, M., Vaidya, S., Jain, L.C.: Advanced Computational Intelligence Paradigms in Healthcare, vol. 3. Springer, Heidelberg (2008)Google Scholar
  6. 6.
    Buchanan, B.G., Shortliffe, E.H.: Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project. Addison-Wesley, Reading (1984)Google Scholar
  7. 7.
    Liebowitz, J.: The Handbook of Applied Expert Systems. CRC Press, Boca Raton (1997)Google Scholar
  8. 8.
    Jain, A., Jain, A., Jain, S., Jain, L.: Artificial Intelligence Techniques in Breast Cancer Diagnosis and Prognosis. World Scientific, Singapore (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Burnside, E.S., Rubin, D.L., Fine, J.P., Shachter, R.D., Sisney, G.A., Leung, W.K.: Bayesian network to predict breast cancer risk of mammographic microcalcifications and reduce number of benign biopsy results. Journal of Radiology (2006)Google Scholar
  10. 10.
    Kahn, C.E., Roberts, L.M., Shaffer, K.A., Haddawy, P.: Construction of a bayesian network for mammographic diagnosis of breast cancer. Computers and Biology and Medicine 27(1), 19–30 (1997)CrossRefGoogle Scholar
  11. 11.
    Karabatak, M., Ince, M.C.: An expert system for detection of breast cancer based on association rules and neural network. Expert Systems with Applications: An International Journal 36(2), 3465–3469 (2009)CrossRefGoogle Scholar
  12. 12.
    Wolberg, W.H., Street, W.N., Mangasarian, O.L.: Machine learning techniques to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77, 163–171 (1994)CrossRefGoogle Scholar
  13. 13.
    Ye, J., Zheng, S., Yang, C.: SVM-based microcalcification detection in digital mammograms. In: Proceedings of the 2008 International Conference on Computer Science and Software Engineering, vol. 6, pp. 89–92 (2008)Google Scholar
  14. 14.
    Roca-Pardiñas, J., Cadarso-Suárez, C., Tahoces, P.G., Lado, M.J.: Assessing continuous bivariate effects among different groups through nonparametric regression models: An application to breast cancer detection. Computational Statistics & Data Analysis 52(4), 1958–1970 (2008)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Gupta, S., Chyn, P., Markey, M.: Breast cancer CADx based on bi-rads descriptors from two mammographic views. Medical Physics 33(6), 1810–1817 (2006)CrossRefGoogle Scholar
  16. 16.
    Good, W., Zheng, B., Chang, Y., Wang, X., Maitz, G., Gur, D.: Multi-image cad employing features derived from ipsilateral mammographic views. In: Proceedings of SPIE, Medical Imaging, vol. 3661, pp. 474–485 (1999)Google Scholar
  17. 17.
    Engeland, S.V., Timp, S., Karssemeijer, N.: Finding corresponding regions of interest in mediolateral oblique and craniocaudal mammographic views. Medical Physics 33(9), 3203–3212 (2006)CrossRefGoogle Scholar
  18. 18.
    Engeland, S.V., Karssemeijer, N.: Combining two mammographic projections in a computer aided mass detection method. Medical Physics 34(3), 898–905 (2007)CrossRefGoogle Scholar
  19. 19.
    Paquerault, S., Petrick, N., Chan, H., Sahiner, B., Helvie, M.A.: Improvement of computerized mass detection on mammograms: Fusion of two-view information. Medical Physics 29(2), 238–247 (2002)CrossRefGoogle Scholar
  20. 20.
    Yuan, Y., Giger, M., Li, H., Luan, L., Sennett, C.: Identifying corresponding lesions from CC and MLO views via correlative feature analysis. In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 323–328. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  21. 21.
    Gupta, S., Zhang, D., Sampat, M.P., Markey, M.K.: Combining texture features from the MLO and CC views for mammographic CADx. Progress in biomedical optics and imaging 7(3) (2006)Google Scholar
  22. 22.
    Zheng, B., Leader, J.K., Abrams, G.S., Lu, A.H., Wallace, L.P., Maitz, G.S., Gur, D.: Multiview-based computer-aided detection scheme for breast masses. Medical Physics 33(9), 3135–3143 (2006)CrossRefGoogle Scholar
  23. 23.
    Zheng, B., Tan, J., Ganott, M.A., Chough, D.M., Gur, D.: Matching breast masses depicted on different views a comparison of three methods. Academic Radiology 16(11), 1338–1347 (2009)CrossRefGoogle Scholar
  24. 24.
    Wei, J., Chan, H., Sahiner, B., Zhou, C., Hadjiiski, L.M., Roubidoux, M.A., Helvie, M.A.: Computer-aided detection of breast masses on mammograms: dual system approach with two-view analysis. Medical Physics 36(10), 4451–4460 (2009)CrossRefGoogle Scholar
  25. 25.
    Pearl, J.: Probabilistic Reasoning in Inteligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
  26. 26.
    Jensen, F., Nielsen, T.: Bayesian Networks and Decision Graphs. Springer, Heidelberg (2007)MATHCrossRefGoogle Scholar
  27. 27.
    Domingos, P., Pazzani, M.: On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning 29, 103–130 (1997)MATHCrossRefGoogle Scholar
  28. 28.
    Heckerman, D., Breese, J.S.: Causal independence for probability assessment and inference using Bayesian networks. IEEE Transactions on Systems, Man and Cybernetics, Part A 26(6), 826–831 (1996)CrossRefGoogle Scholar
  29. 29.
    Lucas, P.J.F.: Bayesian network modelling through qualitative pattern. Artificial Intelligence 163, 233–263 (2005)MATHCrossRefMathSciNetGoogle Scholar
  30. 30.
    Diez, F.: Parameter adjustment in Bayes networks: The generalized noisy or-gate. In: Proceedings of the Ninth Conference on UAI. Morgan Kaufmann, San Francisco (1993)Google Scholar
  31. 31.
    Velikova, M., Lucas, P., de Carvalho Ferreira, N., Samulski, M., Karssemeijer, N.: A decision support system for breast cancer detection in screening programs. In: Proceedings of the 18th biennial European Conference on Artificial Intelligence (ECAI), vol. 178, pp. 658–662 (2008)Google Scholar
  32. 32.
    Velikova, M., Samulski, M., Lucas, P., Karssemeijer, N.: Improved mammographic CAD performance using multi-view information: A Bayesian network framework. Physics in Medicine and Biology 54(5), 1131–1147 (2009)CrossRefGoogle Scholar
  33. 33.
    Murphy, K.: Bayesian Network Toolbox for Matlab, BNT (2007), http://www.cs.ubc.ca/~murphyk/Software/BNT/bnt.html
  34. 34.
    Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a Receiver Operating Characteristic (ROC) curve. Radiology 143, 29–36 (1982)Google Scholar
  35. 35.
    Metz, C., Wang, P., Kronman, H.: A new approach for testing the significance of differences between ROC curves measured from correlated data. In: Information Processing in Medical Imaging, Nijhoff (1984)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Marina Velikova
    • 1
  • Nivea Ferreira
    • 1
  • Maurice Samulski
    • 2
  • Peter J. F. Lucas
    • 1
  • Nico Karssemeijer
    • 2
  1. 1.Institute for Computing and Information SciencesRadboud University NijmegenNijmegenThe Netherlands
  2. 2.Department of RadiologyRadboud University Nijmegen Medical CentreNijmegenThe Netherlands

Personalised recommendations