Advertisement

Bony Structure Suppression in Chest Radiographs

  • M. Loog
  • B. van Ginneken
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4241)

Abstract

Many computer aided diagnosis schemes in chest radiography start with preprocessing steps that try to remove or suppress normal anatomical structures from the image. Examples of normal structures in posteroanterior chest radiographs are bony structures. Removing these kinds of structures can be done quite effectively if the right dual energy images—two radiographic images from the same patient taken with different energies—are available. Subtracting these two radiographs gives a soft-tissue image with most of the rib and other bony structures removed. In general, however, dual energy images are not readily available.

We propose a supervised learning technique for inferring a soft-tissue image from a standard radiograph without explicitly determining the additional dual energy image. The procedure, called dual energy faking, is based on k-nearest neighbor regression, and incorporates knowledge obtained from a training set of dual energy radiographs with their corresponding subtraction images for the construction of a soft-tissue image from a previously unseen single standard chest image.

Keywords

Chest Radiograph Lung Nodule Explicit Scheme Bony Structure Subtraction Image 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shah, P.K., Austin, J.H.M., White, C.S., Patel, P., Haramati, L.B., Pearson, G.D.N., Shiau, M.C., Berkmen, Y.M.: Missed non-small cell lung cancer: Radiographic findings of potentially resectable lesions evident only in retrospect. Radiology 226(3), 235–241 (2003)CrossRefGoogle Scholar
  2. 2.
    Fischbach, F., Freund, T., Röttgen, R., Engert, U., Felix, R., Ricke, J.: Dual-energy chest radiography with a flat-panel digital detector: Revealing calcified chest abnormalities. American Journal of Roentgenology 181, 1519–1524 (2003)Google Scholar
  3. 3.
    Warp, R.J., Dobbins III, J.T.: Quantitative evaluation of noise reduction strategies in dual-energy imaging. Medical Physics 30(2), 190–198 (2003)CrossRefGoogle Scholar
  4. 4.
    Loog, M.: Supervised dimensionality reduction and contextual pattern recognition in medical image processing. Ph.D. Thesis, Image Sciences Institute, Utrecht University, The Netherlands (2004)Google Scholar
  5. 5.
    Kano, A., Doi, K., MacMahon, H., Hassell, D., Giger, M.: Digital image subtraction of temporally sequential chest images for detection of interval change. Medical Physics 21(3), 453–461 (1994)CrossRefGoogle Scholar
  6. 6.
    Katsuragawa, S., Tagashira, H., Li, Q., MacMahon, H., Doi, K.: Comparison of quality of temporal subtraction images obtained with manual and automated methods of digital chest radiography. Journal of Digital Imaging 12(4), 166–172 (1999)CrossRefGoogle Scholar
  7. 7.
    Loeckx, D., Maes, F., Vandermeulen, D., Suetens, P.: Temporal subtraction of thorax CR images using a statistical deformation model. IEEE Transactions on Medical Imaging 22(11), 1490–1504 (2003)CrossRefGoogle Scholar
  8. 8.
    Li, Q., Katsuragawa, S., Ishida, T., Yoshida, H., Tsukuda, S., MacMahon, H., Doi, K.: Contralateral subtraction: A novel technique for detection of asymmetric abnormalities on digital chest radiographs. Medical Physics 27(1), 47–55 (2000)CrossRefGoogle Scholar
  9. 9.
    Shiraishi, J., Katsuragawa, S., Ikezoe, J., Matsumoto, T., Kobayashi, T., Komatsu, K., Matsui, M., Fujita, H., Kodera, Y., Doi, K.: Development of a digital image database for chest radiographs with and without a lung nodule: Receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. American Journal of Roentgenology 174, 71–74 (2000)Google Scholar
  10. 10.
    Ginneken, B., Haar Romeny, B., Viergever, M.A.: Computer-aided diagnosis in chest radiography: A survey. IEEE Transactions on Medical Imaging 20(12), 1228–1241 (2001)CrossRefGoogle Scholar
  11. 11.
    Florack, L.M.J.: Image Structure. In: Computational Imaging and Vision, vol. 10. Kluwer Academic Publishers, Boston (1997)Google Scholar
  12. 12.
    Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Press, Boston (1994)Google Scholar
  13. 13.
    Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, Heidelberg (1996)MATHGoogle Scholar
  14. 14.
    Edwards, A.L.: Multiple Regression and the Analysis of Variance and Covariance. W. H. Freeman, San Francisco (1979)MATHGoogle Scholar
  15. 15.
    Rice, J.A.: Mathematical Statistics and Data Analysis, 2nd edn. Duxbury Press, Belmont (1995)MATHGoogle Scholar
  16. 16.
    Ginneken, B., Katsuragawa, S., ter Haar Romeny, B., Doi, K., Viergever, M.: Automatic detection of abnormalities in chest radiographs using local texture analysis. IEEE Transactions on Medical Imaging 21(2), 139–149 (2002)CrossRefGoogle Scholar
  17. 17.
    MacMahon, H.: Clinical application of CAD in the chest. In: Computer-Aided Diagnosis in Medical Imaging. International Congress Series, vol. 1182, pp. 23–34 (1999)Google Scholar
  18. 18.
    Schilham, A.M.R., van Ginneken, B., Loog, M.: Multi-scale nodule detection in chest radiographs. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 602–609. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  19. 19.
    Xu, X.W., MacMahon, H., Doi, K.: Detection of lung nodule on digital energy subtracted soft-tissue and conventional chest images from a CR system. In: Computer-Aided Diagnosis in Medical Imaging. International Congress Series, vol. 1182, pp. 63–70 (1999)Google Scholar
  20. 20.
    Eskicioglu, A.M., Fisher, P.S.: Image quality measures and their performance. IEEE Transactions on Communications 43(12), 2959–2965 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • M. Loog
    • 1
  • B. van Ginneken
    • 2
  1. 1.The Image GroupIT University of CopenhagenCopenhagenDenmark
  2. 2.Image Sciences InstituteUniversity Medical Center UtrechtUtrechtThe Netherlands

Personalised recommendations