Fluid non-rigid registration combining SIFT and shape information for prostate treatment

In image registration based on fluid model for prostate treatment, the body force that drives the deformation of the template images with only the term of intensity information may have problems in matching structure in prostate images. This paper introduces the fluid non-rigid registration combining SIFT and shape information and quantificational analysis the performance in prostate images to determine the corresponding parameters. Experiments on both synthetic and clinical images show the feasibility of improving the accuracy of prostate image registration, and the correlation coefficient (CC) value for the new method has been increased form 0.75 to 0.80.