Deep Iterative 2D/3D Registration
This addresses the need for accurate and fast registration in clinical applications, representing an incremental improvement over existing hybrid methods.
The paper tackles the problem of achieving high accuracy in deep learning-based 2D/3D registration for clinical use by proposing an end-to-end iterative framework that eliminates the need for a refinement step, resulting in a mean re-projection distance error of 0.60 ± 0.40 mm, a success ratio of 97%, and an average runtime of 8s.
Deep Learning-based 2D/3D registration methods are highly robust but often lack the necessary registration accuracy for clinical application. A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy. However, it also increases the runtime. In this work, we propose a novel Deep Learning driven 2D/3D registration framework that can be used end-to-end for iterative registration tasks without relying on any further refinement step. We accomplish this by learning the update step of the 2D/3D registration framework using Point-to-Plane Correspondences. The update step is learned using iterative residual refinement-based optical flow estimation, in combination with the Point-to-Plane correspondence solver embedded as a known operator. Our proposed method achieves an average runtime of around 8s, a mean re-projection distance error of 0.60 $\pm$ 0.40 mm with a success ratio of 97 percent and a capture range of 60 mm. The combination of high registration accuracy, high robustness, and fast runtime makes our solution ideal for clinical applications.