Semi-automatic Reference Standard Construction for Quantitative Evaluation of Lung CT Registration

  • Keelin Murphy
  • Bram van Ginneken
  • Josien P. W. Pluim
  • Stefan Klein
  • Marius Staring
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5242)

Abstract

An algorithm is presented for the efficient semi-automatic construction of a detailed reference standard for registration in thoracic CT. A well-distributed set of 100 landmarks is detected fully automatically in one scan of a pair to be registered. Using a custom-designed interface, observers locate corresponding anatomic locations in the second scan. The manual annotations are used to learn the relationship between the scans and after approximately twenty manual marks the remaining points are matched automatically. Inter-observer differences demonstrate the accuracy of the matching and the applicability of the reference standard is demonstrated on two different sets of registration results over 19 CT scan pairs.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Betke, M., Hong, H., Ko, J.P.: Landmark detection in the chest and registration of lung surfaces with an application to nodule registration. Medical Image Analysis 7, 265–281 (2003)CrossRefGoogle Scholar
  2. 2.
    Blaffert, T., Wiemker, R.: Comparison of different follow-up lung registration methods with and without segmentation. In: Proc. SPIE, vol. 5370, pp. 1701–1708 (2004)Google Scholar
  3. 3.
    Bookstein, F.L.: Principal Warps: Thin-Plate Splines and the Decomposition of Deformations. IEEE Trans. PAMI 11, 567–585 (1989)CrossRefMATHGoogle Scholar
  4. 4.
    Hu, S., Hoffman, E.A., Reinhardt, J.M.: Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans. Med. Imaging 20(6), 490–498 (2001)CrossRefGoogle Scholar
  5. 5.
    Klein, S., Staring, M., Pluim, J.P.W.: Evaluation of optimization methods for nonrigid medical image registration using mutual information and B-splines. IEEE Trans. Med. Imaging 16(12), 2879–2890 (2007)MathSciNetGoogle Scholar
  6. 6.
    Likar, B., Pernuš, F.: Automatic extraction of corresponding points for the registration of medical images. Medical Physics 26, 1678–1686 (1999)CrossRefGoogle Scholar
  7. 7.
    McClelland, J., Blackall, J., Tarte, S.: A continuous 4D motion model from multiple respiratory cycles for use in lung radiotherapy. Medical Physics 33 (2006)Google Scholar
  8. 8.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  9. 9.
    Saff, E.B., Kuijlaars, A.B.J.: Distributing Many Points on a Sphere. The Mathematical Intelligence 19, 5–11 (1997)MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Thèvenaz, P., Unser, M.: Optimization of mutual information for multiresolution image registration. IEEE Trans. Image Proc. 9(12), 2083–2099 (2000)CrossRefMATHGoogle Scholar
  11. 11.
    Urschler, M., Kluckner, S., Bischof, H.: A Framework for Comparison and Evaluation of Nonlinear Intra-Subject Image Registration Algorithms. In: IJ - 2007 MICCAI Open Science Workshop (2007)Google Scholar
  12. 12.
    Vik, T., Kabusa, S., von Berg, J., Ens, K., Dries, S., Klinder, T., Lorenz, C.: Validation and comparison of registration methods for freebreathing 4D lung CT. In: Proc. SPIE (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Keelin Murphy
    • 1
  • Bram van Ginneken
    • 1
  • Josien P. W. Pluim
    • 1
  • Stefan Klein
    • 1
  • Marius Staring
    • 1
  1. 1.University Medical CenterUtrechtThe Netherlands

Personalised recommendations