Abstract
Intensity-driven image registration does not always produce satisfactory pointwise correspondences in regions of low soft-tissue contrast characteristic of pelvic computed tomography (CT) imaging. Additional information such as manually segmented organ surfaces can be combined with intensity information to improve registration. However, this approach is sensitive to non-negligible surface segmentation errors (delineation errors) due to the relative poor soft-tissue contrast supported by CT. This paper presents an image registration algorithm that mitigates the impact of delineation errors by weighting each surface element by its segmentation uncertainty. This weighting ensures that portions of the surface that are specified accurately are used to guide the registration while portions of the surface that are uncertain are ignored. In our proof-of-principle validation, Monte Carlo simulations based on simple 3D phantoms demonstrate the strengths and weaknesses of the proposed method. These experiments show that registration performance can be improved using surface uncertainty in certain circumstances but not in others. Results are presented for situations when intensity only registration performs best, when intensity plus equally weighted surface registration performs best, and when intensity plus uncertainty weighted surface registration performs best. The algorithm has been applied to register CBCT and FBCT prostate images where the uncertainty of the prostate surface segmentation was estimated using contours drawn by five experts.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Christensen, G., Carlson, B., Chao, K., Yin, P., Grigsby, P., Nguyen, K., Dempsey, J., Lerma, F., Bae, K., Vannier, M., et al.: Image-based dose planning of intracavitary brachytherapy: registration of serial-imaging studies using deformable anatomic templates. International Journal of Radiation Oncology Biology Physics 51(1), 227–243 (2001)
Davies, R., Twining, C., Cootes, T., Waterton, J., Taylor, C.: A minimum description length approach to statistical shape modeling. IEEE Transactions on Medical Imaging 21(5), 525–537 (2002)
Greene, W.H., Chelikani, S., Purushothaman, K., Knisely, J.P.S., Chen, Z., Papademetris, X., Staib, L.H., Duncan, J.S.: Constrained non-rigid registration for use in image-guided adaptive radiotherapy. Medical Image Analysis 13(5), 809 (2009)
Hartkens, T., Hill, D.L.G., Castellano-Smith, A.D., Hawkes, D.J., Maurer Jr., C.R., Martin, A.J., Hall, W.A., Liu, H., Truwit, C.L.: Using Points and Surfaces to Improve Voxel-Based Non-rigid Registration. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002, Part II. LNCS, vol. 2489, pp. 565–572. Springer, Heidelberg (2002)
Joshi, A.A., Shattuck, D.W., Thompson, P.M., Leahy, R.M.: Surface-constrained volumetric brain registration using harmonic mappings. IEEE Transactions on Medical Imaging 26(12), 1657–1669 (2007)
Kurtek, S., Klassen, E., Ding, Z., Jacobson, S., Jacobson, J., Avison, M., Srivastava, A.: Parameterization-invariant shape comparisons of anatomical surfaces. IEEE Transactions on Medical Imaging 30(3), 849 (2011)
Kurtek, S., Klassen, E., Ding, Z., Avison, M.J., Srivastava, A.: Parameterization-Invariant Shape Statistics and Probabilistic Classification of Anatomical Surfaces. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 147–158. Springer, Heidelberg (2011)
Postelnicu, G., Zollei, L., Fischl, B.: Combined volumetric and surface registration. IEEE Transactions on Medical Imaging 28(4), 508 (2009)
Remeijer, P., Rasch, C., Lebesque, J.V., van Herk, M.: A general methodology for three-dimensional analysis of variation in target volume delineation. Medical Physics 26(6), 931–940 (1999)
Rohr, K., Stiehl, H., Sprengel, R., Buzug, T., Weese, J., Kuhn, M.: Landmark-based elastic registration using approximating thin-plate splines. IEEE Transactions on Medical Imaging 20(6), 526–534 (2001)
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 Transactions on Medical Imaging 18(8), 712 (1999)
Wells, W.M., Viola, P., Atsumi, H., Nakajima, S., Kikinis, R.: Multi-modal volume registration by maximization of mutual information. Medical Image Analysis 1(1), 35–51 (1996)
Wu, J., Murphy, M.J., Weiss, E., Sleeman IV, W.C., Williamson, J.: Development of a population-based model of surface segmentation uncertainties for uncertainty-weighted deformable image registrations. Medical Physics 37(2), 607–614 (2010)
Wrz, S., Rohr, K.: Physics-based elastic registration using non-radial basis functions and including landmark localization uncertainties. Computer Vision and Image Understanding 111(3), 263–274 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, C. et al. (2012). SUPIR: Surface Uncertainty-Penalized, Non-rigid Image Registration for Pelvic CT Imaging. In: Dawant, B.M., Christensen, G.E., Fitzpatrick, J.M., Rueckert, D. (eds) Biomedical Image Registration. WBIR 2012. Lecture Notes in Computer Science, vol 7359. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31340-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-31340-0_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31339-4
Online ISBN: 978-3-642-31340-0
eBook Packages: Computer ScienceComputer Science (R0)