Postprint version. Published in Mathematical Biosciences and Engineering, Volume 5, Issue 1, January 1, 2008, pages 125-144.
Copyright © 2008 American Institute of Mathematical Sciences. This is a pre-copy-editing, author-produced PDF of an article accepted for publication in Mathematical Biosciences and Engineering following peer review. The definitive publisher-authenticated version is available online at http://aimsciences.org/journals/displayPapers.jsp?comments=&pubID=219&journID=8&pubString=Volume:%205,%20Number:%201,%20January%202008.
NOTE: At the time of publication, the author Dana Paquin was not yet affiliated with Cal Poly.
Multiscale image registration techniques are presented for the registration of medical images using deformable registration models. The techniques 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 experiments using B-spline free-form deformation registration models demonstrate that ordinary deformable registration techniques fail to produce accurate results 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 multiscale 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 registration of images that contain noise levels well beyond the level at which ordinary deformable registration fails. Numerous image registration experiments demonstrate the accuracy and efficiency of the multiscale registration techniques.