Non-rigid registration of multimodal images (Ultrasound and CT) of Liver using gradient orientation information

Abstract

Image registration is considered as a highly challenging task which is used in various medical applications such as diagnosis and image guided interventions. Registration is performed with medical images captured via different modalities and labeled as moving and fixed images. The transformation of the moving image is achieved by minimizing an objective function through updating the parameters of transformation. The existing techniques have some drawbacks in terms of speed, performance level and accuracy. Considering the limits, a new algorithm for non-rigid registration is proposed in this paper which is executed using the Ultrasound (US) and Computed Tomography (CT) images of Liver. The algorithm includes segmentation of liver surface, selection of best matched slice using similarity measure, calculation of objective function and estimation of transformation. The proposed method is applied to three clinical datasets and quantitative evaluations are conducted. Visual examinations and experimental results verifies a lower level of registration error and a higher level of accuracy which makes the algorithm acceptable for clinical applications.