Performance Comparison of Optimization Methods for Medical Image Registration

Performance Comparison of Optimization Methods for Medical Image Registration

Year:    2014

Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 4 : pp. 507–516

Abstract

In the process of medical image registration, the registration function (also so-called similarity metric) was taken as the objective function, and the multi-parameter optimization method as the tool for obtaining the optimal transformation parameters. In this paper, by the use of the mutual information as the registration function, the Powell method and the genetic algorithm were exerted to explore the optimal transformation parameters respectively, and their optimizing performances were evaluated and compared. The experimental results reveal that the Powell method can cater to both the mono- and multi-modality medical image registrations. Unfortunately, however, the genetic algorithm is not adopted for the medical image registration regardless of the registration accuracy or the running time and needs to be significantly improved.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.3993/jfbi12201404

Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 4 : pp. 507–516

Published online:    2014-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    10

Keywords:    Medical Image Registration