Skip to Main Content
This paper deals with the 3D reconstruction of sparse data in X-ray rotational imaging. Due to the cardiac motion, the number of available projections for this reconstruction is equal to four, which leads to a strongly under-sampled reconstruction problem. We address thus this illness problem through a regularized iterative method. The whole algorithm is divided into two steps. Firstly, a minimal path segmentation step extracts artery tree boundaries. Secondly, a MAP reconstruction comparing L0-norm and L1-norm priors is applied on this extracted coronary tree. The reconstruction optimization process relies on a separable paraboloidal (SPS) algorithm. Some preliminary results are provided on simulated rotational angiograms.