2D/3D registration of patient vasculature from preinterventional computed tomography angiography (CTA) to interventional X-ray angiography is of interest to improve guidance in percutaneous coronary interventions. In this paper we present a novel feature based 2D/3D registration framework, that is based on probabilistic point correspondences, and show its usefulness on aligning 3D coronary artery centerlines derived from CTA images with their 2D projection derived from interventional X-ray angiography. The registration framework is an extension of the Gaussian mixture model (GMM) based point-set registration to the 2D/3D setting, with a modified distance metric. We also propose a way to incorporate orientation in the registration, and show its added value for artery registration on patient datasets as well as in simulation experiments. The oriented GMM registration achieved a median accuracy of 1.06 mm, with a convergence rate of 81% for nonrigid vessel centerline registration on 12 patient datasets, using a statistical shape model. The method thereby outperformed the iterative closest point algorithm, the GMM registration without orientation, and two recently published methods on 2D/3D coronary artery registration.

Gaussian mixture model (GMM), percutaneous coronary intervention (PCI), point-set, statistical shape models (SSM)
dx.doi.org/10.1109/TMI.2014.2300117, hdl.handle.net/1765/63935
IEEE Transactions on Medical Imaging
Department of Cardiology

Baka, N, Metz, C.T, Schultz, C.J, van Geuns, R.J.M, Niessen, W.J, & van Walsum, T.W. (2014). Oriented Gaussian mixture models for nonrigid 2D/3D coronary artery registration. IEEE Transactions on Medical Imaging, 33(5), 1023–1034. doi:10.1109/TMI.2014.2300117