Multi-modality registration by using mutual information with honey bee mating optimization (HBMO)

Chih Hsun Lin, Chung I. Huang, Yung Nien Sun, Ming Huwi Horng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Registration is a popular technique commonly used in medical image processing. In this paper, we propose a new registration algorithm which uses the mutual information (MI) as the similarity measurement function and utilizes a new optimization algorithm, called honey bee mating optimization (HBMO), to obtain the optimal registration. By simulating the biological evolution, HBMO can obtain a set of optimized parameters for registration with the largest similarity measure. By applying the proposed method to medical images, the experimental results showed that the method achieved better accuracy in registration than the conventional Powell's optimization method which is the most commonly used method in medical image registration. Also, the proposed method remained stable and accurate during the experiment of using several different source images. With each source image, we calculated mean SD of the parameters by repeating twenty times.

Original languageEnglish
Title of host publicationProceedings of 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010
Pages13-16
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010 - Kuala Lumpur, Malaysia
Duration: 2010 Nov 302010 Dec 2

Publication series

NameProceedings of 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010

Other

Other2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010
CountryMalaysia
CityKuala Lumpur
Period10-11-3010-12-02

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Multi-modality registration by using mutual information with honey bee mating optimization (HBMO)'. Together they form a unique fingerprint.

Cite this