3D Statistical Shape Models Using Direct Optimisation of Description Length
We describe an automatic method for building optimal 3D statistical shape models from sets of training shapes. Although shape models show considerable promise as a basis for segmenting and interpreting images, a major drawback of the approach is the need to establish a dense correspondence across a training set of example shapes. It is important to establish the correct correspondence, otherwise poor models can result. In 2D, this can be achieved using manual ‘landmarks’, but in 3D this becomes impractical. We show it is possible to establish correspondences automatically, by casting the correspondence problem as one of finding the ‘optimal’ parameterisation of each shape in the training set. We describe an explicit representation of surface parameterisation, that ensures the resulting correspondences are legal, and show how this representation can be manipulated to minimise the description length of the training set using the model. This results in compact models with good generalisation properties. Results are reported for two sets of biomedical shapes, showing significant improvement in model properties compared to those obtained using a uniform surface parameterisation.
KeywordsShape Model Minimum Description Length Active Shape Model Statistical Shape Model Shape Vector
Unable to display preview. Download preview PDF.
- 4.Brett A.D. and C.J. Taylor, “Construction of 3D Shape Models of Femoral Articular Cartialge Using Harmonic Maps”, in MICCAI’00, p. 1205–1214, 2000Google Scholar
- 8.Davies, Rh. H., C.J. Twining, T.F. Cootes, J.C. Waterton and C.J. Taylor, “A Minimum Description Length Approach to Statistical Shape Modelling”, in IEEE trans. Medical Imaging, To appearGoogle Scholar
- 9.Davies, Rh. H., T.F. Cootes, C.J. Twining and C.J. Taylor, “An Information Theoretic Approach to Statistical Shape Modelling”, in British Machine Vision Conference-BMVC’01, p 3–12, 2001Google Scholar
- 10.Fluete, M., S. Lavalee, “Building a Complete Surface Model from Sparse Data Using Statistical Shape Models: Application to Computer Assisted Knee Surgery”, in MICCAI’98, p878–887, 1998Google Scholar
- 11.M. H. Hansen and B. Yu, “Model Selection and the Principle of Minimum Description Length”, Technical Memorandum, Bell Labs, Murray Hill, N.J. 1998.Google Scholar
- 12.Hill, A., A. Thornham and C.J. Taylor, “Model based interpretation of 3D medical images”, in British Machine Vision Conference, BMVC’93, p339–348, 1993Google Scholar
- 13.Joshi et. al, “Gaussian Random Fields on Sub-Manifolds for Characterizing Brain Surfaces”, in IPMI’97, p381–386, 1997Google Scholar
- 17.Press, W.H., S. A. Teukolsky, W. T. Vetterling, B. P. Flannery, Numerical Recipes in C, Cambridge University Press; 1993Google Scholar
- 21.Rueckert, D., Frangi, F., Schnabel, J.A., “Automatic construction of 3D statistical deformation models using non-rigid registration”, MICCAI’01 p77–84. 2001.Google Scholar
- 24.D. Tosun and J.L. Prince, “Hemispherical map for the human brain cortex,” Proc. SPIE Medical Imaging 2001, p 290–300. 2001.Google Scholar
- 25.Wang, Y., B. S. Peterson, and L. H. Staib. “Shape-based 3D surface correspondence using geodesics and local geometry”. CVPR 2000, v. 2: p. 644–51. 2000.Google Scholar