Medical Image Registration Based On Normal Vector Information

With the rapid progress and development of high technologies, the medical imagingtechnologies have provided many imaging equipments, which are more and more assistingthe modern medicine. The computer tomography (CT) and magmatic resonance (MR) haveachieved high performance in medical imaging. At the same time, the functional magmaticresonance imaging (fMRI), positron emission tomography (PET), single photon emissionCT (SPECT), etc.,these functional, metabolic imaging technologies are employed more andmore in medicine. These imaging techniques are providing high-quality anatomy and func-tion information for clinical diagnose and other computer-assistant operation and treatment.They also help people realize the importance of health, which further improve the medi-cal treatment and heath of people. However, the different modality of medical images alsopresents the challenging on how to combine those information and make full use of them.Therefore, the medical image registration with high accuracy and efficiency becomes thepopular research area in recent years.Image registration is to find a geometric transformation that maps a given moving imageinto a fixed image to make them most similar. This technique to align those medical imagesis the pre-work for quantitatively analyzing them. In the framework of registration, how toevaluate the similarity or quantitatively measure how much two images are aligned is one ofthe crucial components. In this paper, we will make a survey of several similarity measures,and make comparisons with another novel measure that is proposed in this paper. We willemploy this method to register the multi-modality medical images as well as confirm itsapplicability. The outline of the work in this paper is as follow:1. This paper will firstly make a survey of the currently popular algorithms in imageregistration in the literature, including the methodology and similarity measure. Wewill present the algorithms in detail as well as their features and applications, giving theexperimental results as well as assessments. The most widely used method—mutual...