Coordinate transformation in 3D image matching by a physics based method-elastic body splines

Any image matching scheme that is based on landmarks requires a coordinate transformation that maps landmark locations in one image to corresponding locations in a second image. The development of an approach to this coordinate transformation, called the elastic body spline (EBS), is outlined. The spline is used to match 3D magnetic resonance images (MRIs) of the breast that are used in the diagnosis and evaluation of breast cancer. The elastic body spline is compared to an affine transformation and the thin plate spline. For breast MRIs, the EBS is found to have superior performance as assessed by several measures of the similarity of the matched images.

[1]  S. Timoshenko,et al.  Theory of elasticity , 1975 .

[2]  R. N. Desmarais,et al.  Interpolation using surface splines. , 1972 .

[3]  J. Meinguet.  Multivariate interpolation at arbitrary points made simple , 1979 .

[4]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  S E Harms,et al.  Magnetic resonance imaging of the breast. , 1992, Magnetic resonance quarterly.

[6]  Jan Flusser,et al.  An adaptive method for image registration , 1992, Pattern Recognit..

[7]  S E Harms,et al.  MR imaging of the breast , 1993, Journal of magnetic resonance imaging : JMRI.