A fast and automatic stereotactic registration with a single CT-slice

The paper presents an algorithm for the automatic registration of a stereotactic frame from a single slice captured by a computed tomography (CT) scanner. Such registration is needed in interventional radiology for CT-image guidance of a robotic assistant. Stereotactic registration is based on a set of line fiducials that produce a set of image points. Our objective is to achieve the automatic registration of a stereotactic frame in the presence of noisy data and outliers. To this end, a new formulation of the stereotactic registration problem with a single image is proposed, for any configuration of the fiducials. With very few fiducials, closed-form and numerical solutions are presented. This comes in useful for building a robust automatic line to point matching algorithm based on the RANSAC statistical method. Simulation and experimental results are presented and highlight the robustness properties of the algorithm. They show that the registration is accurate with moderate computing requirements even for a large amount of outliers.