Medical Image Registration Using Coral Reef Optimization for Substrate Layer

Abstract

Image registration is process of alignment of two or more images. It is used to get more information about the obtained image which is useful for the analysis of the disease. In the proposed method we use three different types of image registration. They are demon registration, image registration by mutual information and difference method. In these methods the alignment is achieved by changing some parameters manually. The degree of alignment of two images is directly proportional to the amount of information obtained. In order to maximize the alignment an optimization algorithm is used. The conventional image registration methods are constrained by many limitations. Hence we use a bio-inspired meta-heuristics and high performance Coral Reef optimization with Substrate Layer (CRO-SL) algorithm. CRO-SL is an advanced method of coral reef optimization based on natural behavior of coral reef. The image registration process comprises of various steps like transformation of registering image, evaluation of performance metrics and finding the optimized value for transformation. A uni-model affine transformation is used in the proposed method. The experimental results show that CRO-SL is a very efficient approach in case of alignment of image in higher degree.