Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$)
This addresses the problem of accurate and efficient image registration for medical interventions, offering a novel approach that improves upon incremental advancements in learning-based and optimization-based methods.
The paper tackles multiview 2D/3D rigid registration for medical interventions by proposing POINT^2, a method that learns 2D point correspondences and estimates 3D pose jointly in a single forward-pass, achieving improved accuracy, robustness, and running time over existing learning-based methods and enhancing optimization-based approaches by tenfold in robustness and speed.
We propose to tackle the problem of multiview 2D/3D rigid registration for intervention via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$). $\text{POINT}^2$ learns to establish 2D point-to-point correspondences between the pre- and intra-intervention images by tracking a set of random POIs. The 3D pose of the pre-intervention volume is then estimated through a triangulation layer. In $\text{POINT}^2$, the unified framework of the POI tracker and the triangulation layer enables learning informative 2D features and estimating 3D pose jointly. In contrast to existing approaches, $\text{POINT}^2$ only requires a single forward-pass to achieve a reliable 2D/3D registration. As the POI tracker is shift-invariant, $\text{POINT}^2$ is more robust to the initial pose of the 3D pre-intervention image. Extensive experiments on a large-scale clinical cone-beam CT (CBCT) dataset show that the proposed $\text{POINT}^2$ method outperforms the existing learning-based method in terms of accuracy, robustness and running time. Furthermore, when used as an initial pose estimator, our method also improves the robustness and speed of the state-of-the-art optimization-based approaches by ten folds.