-
Abstract
Multiscale image registration techniques are presented for the reg-
istration of medical images using deformable registration models. The tech-
niques are particularly effective for registration problems in which one or both
of the images to be registered contains significant levels of noise. A brief
overview of existing deformable registration techniques is presented, and exper-
iments using B-spline free-form deformation registration models demonstrate
that ordinary deformable registration techniques fail to produce accurate re-
sults in the presence of significant levels of noise. The hierarchical multiscale
image decomposition described in E. Tadmor, S. Nezzar, and L. Vese's, ''A
multiscale image representation using hierarchical (BV,L2) decompositions''
(Multiscale Modeling and Simulations, 2 (2004): 4, pp. 554-579) is reviewed,
and multiscale image registration algorithms are developed based on the mul-
tiscale decomposition. Accurate registration of noisy images is achieved by
obtaining a hierarchical multiscale decomposition of the images and iteratively
registering the resulting components. This approach enables a successful reg-
istration of images that contain noise levels well beyond the level at which
ordinary deformable registration fails. Numerous image registration experi-
ments demonstrate the accuracy and efficiency of the multiscale registration
techniques.
Mathematics Subject Classification: Primary: 68U10; Secondary: 92C55, 62P10, 94A08.
\begin{equation} \\ \end{equation}
-
Access History
-