ABSTRACT
Image Registration is the process of transforming different sets of medical image data into one coordinate system. Data may have different scan images from different times or from different viewpoints. A common task within medical image analysis is the automatic registration of 2D/3D images of a patient taken at different times / different positions, i.e. Mono-modality case. This task is very useful to detect any pathological evolution and to compute quantitative measures of this evolution. The most important application is the matching of images taken from different modalities, i.e. different sensing devices called as multi-modal registration. This process allows the physician to combine information visually from any combination of imaging modalities and will prove to be extremely beneficial for the surgeon during any decision making processes (Pluim et al 2003).
This chapter concentrates on mono-modal image registration, Multi modal image registration, Intensity vs Feature based registration, Similarity measures like correlation coefficients, Mutual information, Geometric transformation, Optimization techniques, Different approaches and its implementation, Applications of medical image registration and case study are explained. The optimization method can quickly produce optimal solutions that reduce the computation time of the registration and error rate during classification.
