Adaptive region intensity based rigid ultrasound and CT image registration

Zhijun Zhang

Abstract: Rigid registration of intraoperative ultrasound (US) and CT is an important technique to provide real-time guidance for preoperative images and models. Due to the speckle noise and artefacts in US images, accurate registration of CT and US is still a challenging problem. We propose an adaptive region intensity based CT and US registration method. The registration is initialized by matching the distinctive regions of CT and US images. Then the registration is a multistage process in which the regions in US used will be adaptively updated at each stage. The registration problem is considered as a global similarity energy optimization and high local statistical dependency regions selection process. Performances of our method and other intensity based method are evaluated with simulated and real datasets. Experiments results show the improvement of our registration method in robustness and accuracy.