Feature Detection with Automatic Scale Selection
International Journal of Computer Vision
3D reconstruction of coronary stents in vivo based on motion compensated x-ray angiograms
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Hi-index | 0.00 |
New drug eluting stents are less radiopaque than bare metal stents and therefore difficult to see with conventional X-ray coronary angiography. 2D StentBoost and intravascular ultrasound (IVUS) are routinely used to evaluate stent deployment and vessel apposition during a percutaneous coronary intervention. IVUS images give cross-sectional information about the stent lumen and surrounding tissue. 2D StentBoost is a boosted angiogram sequence and visualizes the geometry of the deployed stent from a fixed viewing direction. Three-dimensional motion compensated volumetric stent reconstruction has been developed to give insight into the 3D geometry of the stent. Markers on the balloon wire are used to motion compensate cardiac rotational angiography acquisitions. In this paper we present the effect of automated marker detection on in vivo volumetric cardiac stent reconstructions. Automated or semi-automated marker detection reduces user interaction, potentially reduces total processing time, and increases detection results which leads to higher quality of stent reconstructions.