Quantitative Evaluation of Intrinsic Registration Methods for Medical Images

Abstract

Combining complementary information from two or more images by sitting up geometrical correspondence between them is called image registration. Image registration is one of the important steps in image-guided surgery and several methods have been developed for the accurate registration of medical images. In this paper, we present a comparative analyse of intrinsic registration methods for medical images. The analysis begins by the detail investigation of each registration method, covering its features, advantages, issues and challenges. Then, a comprehensive experimentation is carried out to determine the performance of every registration method. The aim is to provide a comprehensive knowledge on the work that has been developed in a compact form for both researchers and clinicians.