Reliable 2D–3D Registration in Dynamic Stereo-Radiography With Energy Barrier Constraints

Abstract

2D-3D registration of native anatomy in dynamic stereo-radiography is a fundamental task in orthopaedics methods that facilitates understanding of joint-level movement. Registration is commonly performed by optimizing a similarity metric which compares the appearances of captured radiographs to computed tomography-based digitally reconstructed radiographs, rendered as a function of pose. This optimization-based framework can accurately recover the pose of native anatomy in stereo-radiographs, but encounters convergence issues in practice, thus limiting the reliability of fully automatic registration. The current work improves the robustness of optimization-based 2D-3D registration through the introduction of data-driven constraints that restrict the set of evaluated pose candidates. Energy-based models are first developed to indicate the viability of anatomic poses, conditioned on target radiographs. Registration is then performed by ensuring that optimization methods search within regions that contain feasible poses, as dictated by energy-based models. The constraints which define these regions of interest are referred to as Energy Barrier Constraints. Experiments with stereo-radiographs capturing glenohumeral anatomy were performed to evaluate the proposed methods. Mean errors of 3.2-5.3 and 2.4-4.8 degrees or mm were observed for scapula and humerus degrees of freedom, respectively, when optimizing a conventional similarity metric. These errors were improved to 0.2-0.7 and 0.4-4.1 degrees or mm when augmenting the similarity metric with the proposed techniques. Results suggest that the introduced methods may benefit optimization-based 2D-3D registration through improved reliability.