Transcatheter Aortic Valve Implantation (TAVI) is a new minimal-invasive intervention for implanting prosthetic valves in patients with aortic stenosis. This procedure is associated with adverse effects like paravalvular leakage, stroke, and coronary obstruction. Accurate automated sizing for planning and patient selection is expected to reduce these adverse effects. Segmentation of the aortic root in CTA is pivotal to enable automated sizing and planning. We present a fully automated segmentation algorithm to extract the aortic root from CTA images consisting of a number of steps: first, ascending aorta and aortic root centerline were extracted. Subsequently, high intensities due to calcifications are masked to improve segmentation. Next, the aortic root is represented in cylindrical coordinates. Finally, the aortic root is segmented using 3D normalized cuts. We validated the method against manual delineations by calculating Dice coefficients and average distances. The method successfully segmented the aortic root in all 20 image datasets. The mean Dice coefficient was 0.945±0.03 and mean radial absolute error was 0.74
0.39 mm. The proposed algorithm showed accurate results compared to manual segmentations.