Title :
NURBS for the geometrical modeling of a new family of Compact-Supported Radial Basis Functions for elastic registration of medical images
Author :
García-Pérez, Verónica ; Tristán-Vega, Antonio ; Aja-Fernández, Santiago
Author_Institution :
Image Process. Lab., Univ. of Valladolid, Valladolid, Spain
fDate :
Aug. 31 2010-Sept. 4 2010
Abstract :
In this paper we propose a novel approach to design a family of Radial Basis Functions with Compact Support applied to elastic registration of medical images. The proposed method is based on Non-Uniform Rational B-Spline theory, which introduce a number of practical properties. The proposed method allows to design almost perfect equally distributed functions which fulfill most of the requirements identified in the recent literature. The Radial Basis Function is merely parametrized by the symmetric desired curvature at peak-and-tails. Properties of the function are numerically compared with foregoing RBFs. Preliminary experimental results indicate its suitability and benefits in registration of medical images.
Keywords :
geometry; image registration; medical image processing; radial basis function networks; splines (mathematics); NURBS; compact-supported radial basis functions; elastic registration; geometrical modeling; medical images; nonuniform rational B-spline theory; peak-and-tails; symmetric desired curvature; Biomedical imaging; Image registration; Proposals; Spline; Surface reconstruction; Surface topography; Topology; Algorithms; Elasticity; Humans; Image Interpretation, Computer-Assisted; Magnetic Resonance Imaging; Models, Theoretical;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE
Conference_Location :
Buenos Aires
Print_ISBN :
978-1-4244-4123-5
DOI :
10.1109/IEMBS.2010.5628055