In the current clinical work ow of endovascular abdominal aortic repairs (EVAR) a stent graft is inserted into the aneurysmatic aorta under 2D angiographic imaging. Due to the missing depth information in the X-ray visualization, it is highly dificult in particular for junior physicians to place the stent graft in the preoperatively defined position within the aorta. Therefore, methods for accurate stent graft recognition or segmentation in uoroscopy images are highly required. In this paper, we present a novel algorithm to automatically match a 3D model of the stent graft to an intraoperative 2D image showing the device. By an automatic preprocessing and choosing a global-to-local registration approach, we are able to abandon any user interaction and still meet the desired robustness. Our method applies constraints that correspond to the geometric model of the stent graft. The complexity of our registration scheme is reduced by a semi-simultaneous optimization strategy. Validation of our algorithm is performed on synthetic as well as real interventional data provided by our clinical partners. The method is able to match the stent graft model to the 2D image data with good accuracy.     «

In the current clinical work ow of endovascular abdominal aortic repairs (EVAR) a stent graft is inserted into the aneurysmatic aorta under 2D angiographic imaging. Due to the missing depth information in the X-ray visualization, it is highly dificult in particular for junior physicians to place the stent graft in the preoperatively defined position within the aorta. Therefore, methods for accurate stent graft recognition or segmentation in uoroscopy images are highly required. In this paper, we...     »