Medical image registration is one of the processes involved in medical image analysis. During the process, an image will be computed and transform it for mapping the reference image to the target image to analyze the similarity merits as to help in diagnosis the situation in the medical field. However, the accuracy of the image registration is in question, might be improved if we can make use some optimization during the image registration process. In this research, we propose an enhancement of image registration algorithms based on monomodal registration by incorporating Cuckoo Search (CS) method for Lévy flight generation while simultaneously modifying and optimizing it to work on MRI image scanners, specifically to detect brain cancer. The performance of the proposed monomodal registration with CS algorithm was compared with basic traditional monomodal registration. The experimental results were validated by measuring the Normalized Mutual Information (NMI) and CPU run-time for all cases investigated. Our results show that the proposed monomodal registration with CS algorithm achieved the best 2% improved in NMI results and 42% reduced in CPU run-time. The method evolved to be more promising and computationally efficient for medical image registration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.