Image Registration Accuracy Estimation Without Ground Truth Using Bootstrap

  • Jan Kybic
  • Daniel Smutek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4241)


We consider the problem of estimating the local accuracy of image registration when no ground truth data is available. The technique is based on a statistical resampling technique called bootstrap. Only the two input images are used, no other data are needed. The general bootstrap uncertainty estimation framework described here is in principle applicable to most of the existing pixel based registration techniques. In practice, a large computing power is required. We present experimental results for a block matching method on an ultrasound image sequence for elastography with both known and unknown deformation field.


Image Registration Geometrical Error Registration Algorithm Ground Truth Data Block Match 
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.
    Brown, L.: A survey of image registration techniques. ACM Computing Surveys 24(4), 326–376 (1992)CrossRefGoogle Scholar
  2. 2.
    Lester, H., Arridge, S.R.: A survey of hierarchical non-linear medical image registration. Pattern Recognition 32(1), 129–149 (1999)CrossRefGoogle Scholar
  3. 3.
    Maintz, J., Viergever, M.A.: A survey of medical image registration. Medical Image Analysis 2(1), 1–36 (1998)CrossRefGoogle Scholar
  4. 4.
    Pluim, J., Maintz, J.B.A., Viergever, M.A.: Mutual-information-based registration of medical images: A survey. IEEE Transactions on Medical Imaging 22(8), 986–1004 (2003)CrossRefGoogle Scholar
  5. 5.
    van den Elsen, P.A., Pol, E.J.D., Viergever, M.A.: Medical image matching—A review with classification. IEEE Engineering in Medicine and Biology, 26–39 (1993)Google Scholar
  6. 6.
    Zitová, B., Flusser, J.: Image registration methods: a survey. Image and Vision Computing (21), 977–1000 (2003)CrossRefGoogle Scholar
  7. 7.
    Efron, B., Tibshirani, R.: An Introduction to the Bootstrap. Monographs on Statistics and Applied Probability, vol. 57. Chapman & Hall, CRC (1993)Google Scholar
  8. 8.
    Zoubir, A.M., Boashash, B.: The bootstrap and its applications in signal processing. IEEE Signal Processing Magazine, 56–76 (1998)Google Scholar
  9. 9.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern classification, 2nd edn. Wiley Interscience Publication. John Wiley, New York (2001)zbMATHGoogle Scholar
  10. 10.
    Ophir, J., Kallel, F., Varghese, T., Konofagou, E., Alam, S.K., Garra, B., Krouskop, T., Righetti, R.: Elastography: Optical and acoustic imaging of acoustic media. C. R. Acad. Sci. Paris 2(8), 1193–1212 (2001); serie IVGoogle Scholar
  11. 11.
    Ophir, J., Alam, S., Garra, B., Kallel, F., Konofagou, E., Krouskop, T., Varghese, T.: Elastography: ultrasonic estimation and imaging of the elastic properties of tissues. Proc. Instn. Mech. Engrs. 213, 203–233 (1999)Google Scholar
  12. 12.
    Washington, C.W., Miga, M.I.: Modality independent elastography (MIE): A new approach to elasticity imaging. IEEE Transactions on Medical Imaging, 1117–1126 (2004)Google Scholar
  13. 13.
    Kybic, J., Smutek, D.: Estimating elastic properties of tissues from standard 2d ultrasound images. In: Walker, W.F., Emelianov, S.Y. (eds.) Medical Imaging 2005: Ultrasonic Imaging and Signal Processing, Bellingham, Washington, USA. Progress in Biomedical Optics and Imaging, vol. 6, pp. 184–195. SPIE (2005)Google Scholar
  14. 14.
    Kybic, J., Smutek, D.: Computational elastography from standard ultrasound image sequences by global trust region optimization. In: Christensen, G.E., Sonka, M. (eds.) IPMI 2005. LNCS, vol. 3565, pp. 299–310. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  15. 15.
    Fang, J., Huang, T.S.: Some experiments on estimating the 3-D motion parameters of a rigid body from two consecutive image frames. IEEE Trans. Pattern Anal. Mach. Intell 3(65) (1984)Google Scholar
  16. 16.
    Snyder, M.A.: The precision of 3-D parameters in correspondence based techniques: the case of uniform translational motion in rigid environment. IEEE Trans. Pattern Anal. Mach. Intell. 5(11), 523–528 (1998)Google Scholar
  17. 17.
    Haralick, R.M., Joo, H., Lee, C.N., Zhuang, X., Vaidya, V.G., Kim, M.B.: Pose estimation from corresponding point data. IEEE Trans. Systems, Man and Cybernetics 6(19), 1426–1446 (1989)CrossRefGoogle Scholar
  18. 18.
    Davis, C.Q., Freeman, D.M.: Statistics of subpixel registration algorithms based on spatiotemporal gradients or block matching. Optical Engineering 4(37), 1290–1298 (1998)CrossRefGoogle Scholar
  19. 19.
    Maurer, C.J., Fitzpatrick, J., Wang, M., Galloway, R.J., Maciunas, R., Allen, G.: Registration of head volume images using implantable fiducial markers. IEEE Transactions on Medical Imaging 16(4) (1997)Google Scholar
  20. 20.
    West, J., Fitzpatrick, J.M., Wang, M.Y., Dawant, B.M., Maurer, C.R.J., Kessler, R.M., Maciunas, R.J., Barillot, C., Lemoine, D., Collignon, A., Maes, F., Suetens, P., Vandermeulen, D., van den Elsen, P.A., Napel, S., Sumanaweera, T.S., Harkness, B., Hemler, P.F., Hill, D.L.G., Hawkes, D.J., Studholme, C., Maintz, J.B.A., Viergever, M.A., Malandain, G., Pennec, X., Noz, M.E., Maguire, G.Q.J., Pollack, M., Pelizzari, C.A., Robb, R.A., Hanson, D., Woods, R.P.: Comparison and evaluation of retrospective intermodality brain image registration techniques. Journal of Computer Assisted Tomography 21(4), 554–568 (1997)CrossRefGoogle Scholar
  21. 21.
    Jannin, P., Fitzpatrick, J., Hawkes, D., Pennec, X., Shahidi, R., Vannier, M.: Validation of medical image processing in image-guided therapy. IEEE Trans. on Medical Imaging 21(12), 1445–1449 (2002)CrossRefGoogle Scholar
  22. 22.
    Nicolau, S., Pennec, X., Soler, L., Ayache, N.: Evaluation of a new 3D/2D registration criterion for liver radio-frequencies guided by augmented reality. In: Intl. Symp. on Surgery Sim. and Soft Tissue Model, pp. 270–283 (2003)Google Scholar
  23. 23.
    Kanatani, K.: Geometric computation for machine vision. Oxford University Press, Inc., New York (1993)zbMATHGoogle Scholar
  24. 24.
    Kanatani, K.: Analysis of 3-d rotation fitting. IEEE Trans. Pattern Anal. Mach. Intell 16(5), 543–549 (1994)CrossRefGoogle Scholar
  25. 25.
    Anandan, P.: A computational framework and an algorithm for the measurement of visual motion. International Journal of Computer Vision 2(3), 283–310 (1989)CrossRefGoogle Scholar
  26. 26.
    Heeger, D.J.: Optical flow using spatiotemporal filters. International Journal of Computer Vision 1(4), 279–302 (1988)CrossRefGoogle Scholar
  27. 27.
    Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. In: Proc. Conf. on Computer Vision and Pattern Recognition, Mauii, Hawaii, pp. 310–315. IEEE Computer Society, Los Alamitos (1991)CrossRefGoogle Scholar
  28. 28.
    Pennec, X., Thirion, J.P.: A framework for uncertainty and validation of 3d registration methods based on points and frames. International Journal of Computer Vision 25(3), 203–229 (1997)CrossRefGoogle Scholar
  29. 29.
    Kybic, J., Unser, M.: Fast parametric elastic image registration. IEEE Transactions on Image Processing 12(11), 1427–1442 (2003)CrossRefGoogle Scholar
  30. 30.
    Thévenaz, P., Ruttimann, U.E., Unser, M.: A pyramid approach to subpixel registration based on intensity. IEEE Transactions on Image Processing 7(1), 1–15 (1998)CrossRefMathSciNetGoogle Scholar
  31. 31.
    Thévenaz, P., Unser, M.: Optimization of mutual information for multiresolution image registration. IEEE Transactions on Image Processing 9(12), 2083–2099 (2000)CrossRefzbMATHGoogle Scholar
  32. 32.
    Szeliski, R., Coughlan, J.: Spline-based image registration. International Journal of Computer Vision 22, 199–218 (1997)CrossRefGoogle Scholar
  33. 33.
    Maes, F., Collignong, A., Vandermeulen, D., Marchal, G., Suetens, P.: Multimodality image registration by maximization of mutual information. IEEE Transactions on Medical Imaging 16(2), 187–198 (1997)CrossRefGoogle Scholar
  34. 34.
    Rösch, P., Weese, J., Netsch, T., Quist, M., Penney, G., Hill, D.: Robust 3D deformation field estimation by template propagation. In: Delp, S.L., DiGoia, A.M., Jaramaz, B. (eds.) MICCAI 2000. LNCS, vol. 1935, pp. 521–530. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  35. 35.
    Rueckert, D., Clarkson, M.J., Hill, D.L.G., Hawkes, D.J.: Non-rigid registration using higher-order mutual information. In: Proceedings of SPIE Medical Imaging 2000: Image Processing, pp. 438–447 (2000)Google Scholar
  36. 36.
    Pluim, J.P.W., Maintz, J.B.A., Viergever, M.A.: Image registration by maximization of combined mutual information and gradient information. IEEE Transactions Med. Imag. 19(8) (2000)Google Scholar
  37. 37.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Inteligence 17, 185–203 (1981)CrossRefGoogle Scholar
  38. 38.
    Bro-Nielsen, M., Gramkow, C.: Fast fluid registration of medical images. In: Höhne, K.H., Kikinis, R. (eds.) Visualization in Biomedical Computing, pp. 267–276. Springer, Heidelberg (1996)Google Scholar
  39. 39.
    Morsy, A., Ramm, O.: 3D ultrasound tissue motion tracking using correlation search. IEEE Trans. Ultr. Ferro. & Freq. Cont. 20, 151–159 (1998)Google Scholar
  40. 40.
    Ourselin, S., Roche, A., Prima, S., Ayache, N.: Block matching: A general framework to improve robustness of rigid registration of medical images. In: Delp, S.L., DiGoia, A.M., Jaramaz, B. (eds.) MICCAI 2000. LNCS, vol. 1935, pp. 557–566. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  41. 41.
    Unser, M., Aldroubi, A., Eden, M.: B-Spline signal processing: Part I–Theory. IEEE Transactions on Signal Processing 41(2), 821–833 (1993) (best paper award)CrossRefzbMATHGoogle Scholar
  42. 42.
    Unser, M., Aldroubi, A., Eden, M.: B-Spline signal processing: Part II–Efficient design and applications. IEEE Transactions on Signal Processing 41(2), 834–848 (1993)CrossRefzbMATHGoogle Scholar
  43. 43.
    Unser, M.: Splines: A perfect fit for signal and image processing. IEEE Signal Processing Magazine 16(6), 22–38 (1999)CrossRefGoogle Scholar
  44. 44.
    Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C, 2nd edn. Cambridge University Press, Cambridge (1992)zbMATHGoogle Scholar
  45. 45.
    Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale minimization. Mathematical Programming (45), 503–528 (1989)CrossRefMathSciNetGoogle Scholar
  46. 46.
    Brusseau, E., Fromageau, J., Rognin, N., Delacharte, P., Vray, D.: Local estimation of RF ultrasound signal compression for axial strain imaging: theoretical developments and experimental design. IEEE Engineering in Medicine and Biology Magazine 21(4), 86–94 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jan Kybic
    • 1
  • Daniel Smutek
    • 2
  1. 1.Center for Machine PerceptionCzech Technical UniversityPragueCzech Republic
  2. 2.Faculty of Medicine ICharles UniversityPragueCzech Republic

Personalised recommendations