Gradient-based registration of 3D MR and 2D x-ray images

In this paper we present a novel method for registering a 3D MR image to 2D x-ray images with the final goal to estimate the position and orientation of the patient during surgery or external beam radiotherapy. By using 3D MR preoperative images instead of CT images we increase a soft tissue contrast and reduce the dose delivered to the patient. Such an approach, however, makes the registration difficult because the images of different modalities (MR and x-ray) and different domains (3D and 2D) need to be registered. We address this problem by finding the best match between 2D projection images of the 3D MR gradient image and the x-ray gradient image. The method was examined by using the Visible Human CT and MR data of the pelvis and hips. The experimental results show that in 60% of registrations a target registration error smaller than 10 mm was achieved.