Advertisement

Generalised Overlap Measures for Assessment of Pairwise and Groupwise Image Registration and Segmentation

  • William R. Crum
  • Oscar Camara
  • Daniel Rueckert
  • Kanwal K. Bhatia
  • Mark Jenkinson
  • Derek L. G. Hill
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3749)

Abstract

Effective validation techniques are an essential pre-requisite for segmentation and non-rigid registration techniques to enter clinical use. These algorithms can be evaluated by calculating the overlap of corresponding test and gold-standard regions. Common overlap measures compare pairs of binary labels but it is now common for multiple labels to exist and for fractional (partial volume) labels to be used to describe multiple tissue types contributing to a single voxel. Evaluation studies may involve multiple image pairs. In this paper we use results from fuzzy set theory and fuzzy morphology to extend the definitions of existing overlap measures to accommodate multiple fractional labels. Simple formulas are provided which define single figures of merit to quantify the total overlap for ensembles of pairwise or groupwise label comparisons. A quantitative link between overlap and registration error is established by defining the overlap tolerance. Experiments are performed on publicly available labeled brain data to demonstrate the new measures in a comparison of pairwise and groupwise registration.

Keywords

Registration Error Target Registration Error Multiple Label Binary Label Multiple Tissue Type 
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.

References

  1. 1.
    Collins, D., Dai, W., Peters, T., Evans, A.: Automatic 3D model-based neuroanatomical segmentation. Human Brain Mapping 3, 190–208 (1995)CrossRefGoogle Scholar
  2. 2.
    Chalana, V., Kim, Y.: A methodology for evaluation of boundary detection algorithms on medical images. IEEE Transactions on Medical Imaging 16(5), 642–652 (1997)CrossRefGoogle Scholar
  3. 3.
    Beauchemin, M., Thomson, K.P.B.: The evaluation of segmentation results and the overlapping area matrix. International Journal of Remote Sensing 18(18), 3895–3899 (1997)CrossRefGoogle Scholar
  4. 4.
    Bello, F., Colchester, A.C.F.: Measuring global and local spatial correspondence using information theory. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 964–973. Springer, Heidelberg (1998)Google Scholar
  5. 5.
    Gerig, G., Jomier, M., Chakos, M.: Valmet: A new validation tool for assessing and improving 3D object segmentation. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 516–528. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Crum, W.R., Griffin, L.D., Hill, D.L.G., Hawkes, D.J.: Zen and the Art of Medical Image Registration: Correspondence, Homology and Quality. NeuroImage 20, 1425–1437 (2003)CrossRefGoogle Scholar
  7. 7.
    Bloch, I.: Fuzzy spatial relationships for image processing and interpretation: a review. Image and Vision Computing 23(2), 89–110 (2005)CrossRefGoogle Scholar
  8. 8.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Non-rigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  9. 9.
    Bhatia, K.K., Hajnal, J.V., Puri, B.K., Edwards, A.D., Rueckert, D.: Consistent groupwise non-rigid registration for atlas construction. In: IEEE Symposium on Biomedical Imaging (ISBI), Arlington, pp. 908–911 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • William R. Crum
    • 1
  • Oscar Camara
    • 1
  • Daniel Rueckert
    • 2
  • Kanwal K. Bhatia
    • 2
  • Mark Jenkinson
    • 3
  • Derek L. G. Hill
    • 1
  1. 1.Centre for Medical Image Computing, Dept. of Medical PhysicsUniversity College LondonUK
  2. 2.Visual Information Processing, Department of ComputingImperial College LondonUK
  3. 3.FMRIB Centre, John Radcliffe HospitalUniversity of OxfordUK

Personalised recommendations