Robust 3-D/2-D registration of CT and MR to X-ray images based on gradient reconstruction

Objective A novel 3-D/2-D registration method based on matching 3-D pre-interventional image gradients and coarsely reconstructed 3-D gradients from intra-interventional 2-D images is presented. Material and methods The novel method establishes correspondences between two sets of gradients by searching for correspondences along normals to anatomical structures in 3-D images, while the final correspondences are established in an iterative process, combining the robust random sample consensus algorithm (RANSAC) and a special gradient matching criterion function. The proposed method was evaluated by the publicly available standardized evaluation methodology for 3-D/2-D registration, consisting of 3-D rotational X-ray, computed tomography (CT), magnetic resonance (MR), and 2-D X-ray images of two spine segments, and evaluation criteria. Results Preliminary results show significant improvement in robustness (capture range and success rate) over three well established intensity-based, gradient-based, and reconstruction-based methods. Conclusion The 3-D/2-D gradient reconstruction-based registration method efficiently combines the advantages of gradient and reconstruction-based methods, thereby enabling robust registration of CT and MR to only two X-ray images, while keeping the computational demands low.