A non-rigid medical image registration method based on improved linear elastic model

摘要

Non-rigid medical image registration is an important research project of medical image processing; it is the basis of medical image fusion. Relative to rigid image, the deformation of non-rigid image is more serious and more complicated. According to the characteristics of non-rigid medical image deformation, this paper proposes an adaptive non-rigid medical image registration algorithm. Firstly, it is based on global registration; secondly, it is about extracting feature points of global registration image and the reference image, and then generating irregular triangle grid according to extracted feature points. Finally, local accurate image registration is achieved using the minimum potential energy as a similar measure. Experimental results show that relative to the traditional non-rigid registration algorithm, this algorithm not only ensures the registration accuracy but also enhances the robustness and anti-noise of registration algorithm.