A framework for automatic creation of gold-standard rigid 3D-2D registration datasets

Purpose: Advanced image-guided medical procedures incorporate 2D intra-interventional information into pre-interventional 3D image and plan of the procedure through 3D/2D image registration (32R). To enter clinical use, and even for publication purposes, novel and existing 32R methods have to be rigorously validated. The performance of a 32R method can be estimated by comparing it to an accurate reference or gold standard method (usually based on fiducial markers) on the same set of images (gold standard dataset). Objective validation and comparison of methods are possible only if evaluation methodology is standardized, and the gold standard dataset is made publicly available. Currently, very few such datasets exist and only one contains images of multiple patients acquired during a procedure. To encourage the creation of gold standard 32R datasets, we propose an automatic framework.

Methods: The framework is based on rigid registration of fiducial markers. The main novelty is spatial grouping of fiducial markers on the carrier device, which enables automatic marker localization and identification across the 3D and 2D images.

Results: The proposed framework was demonstrated on clinical angiograms of 20 patients. Rigid 32R computed by the framework was more accurate than that obtained manually, with the respective target registration error below 0.027 mm compared to 0.040 mm.

Conclusion: The framework is applicable for gold standard setup on any rigid anatomy, provided that the acquired images contain spatially grouped fiducial markers. The gold standard datasets and software will be made publicly available.