Investigations on image registration techniques for monomodal and Multimodal brain images

Abstract

Registration issues in medical image processing techniques are newlinemuch more important than those of other image processing techniques newlineThe main criterion of registration is to fuse the sets of data with the newlinevariations if any or with their similarities into a single data These sets of newlinedata are acquired by sampling the same scene or object at different times or newlinefrom different perspectives in different coordinate systems It is used in newlinecomputer vision medical imaging military automatic target recognition and newlinecompiling and analyzing images and data from satellites Registration is newlinenecessary in order to be able to compare or integrate the data obtained from newlinethese different measurements Such data is very essential in medicine for newlinedoctors to plan for surgery newlineMedical image registration has advanced at a fast pace during the newlinelast ten years creating new applications and opportunities In addition the newlinenumber of clinical applications of image registration is increasing Special newlineattention has to be given to quality in order to perform image registration newlineefficiently In the past entropy based methods were used The registration newlinesolution is complicated as there may be misregistrations This does not newlineproduce the required registered images Brain image registrations using newlinetransforms are automatic and have a number of interesting features that can newlinesimplify the clinical applications A number of other image registrations newlinemethods have been introduced but registration using transforms remains the newlinemethod that offers most of the optimal and user friendly features and newlinebenefits Thus more research on enhancing the performance of these image newlineregistration methods is the need of the day newline newline newline