A Review of Deformation Models in Medical Image Registration

The main task of medical image registration is to match different modal images or the same modal images of different periods to provide the doctor with richer diagnostic information. Image registration has been widely used in image diagnostics, image-guided surgical planning and real-time interventional surgical navigation. The deformation model is a key part of the image registration process and can drive the image deformation to achieve a perfect match of the same organization in the two images. In practical application, it is important to establish a reasonable registration deformation model according to the research object, which directly affects the registration results. This paper presents a review of the deformation models used in medical image registration. The deformation model is summarized with respect to four aspects: the elastic image model, the viscoelastic image model, the optical flow model and the prior knowledge model. We primarily summarize the deformation models with good registration results in recent years and analyze their adaptability and existing defects. The purpose of this paper is to provide a reference for the selection of a deformation model.