%0 Journal Article
%J Med Phys
%D 2014
%T Cardiac C-arm computed tomography using a 3D + time ROI reconstruction method with spatial and temporal regularization
%A Mory, C.
%A Auvray, V.
%A Zhang, B.
%A Grass, M.
%A Schäfer, D.
%A S.J. Chen
%A J.D. Carroll
%A Rit, S.
%A Peyrin, F.
%A Douek, P.
%A Boussel, L.
%K Allemagne
%K categ_mixte
%K Imagerie Coeur - Vaisseaux - Poumons
%K Imagerie tomographique et thérapie par rayonnement
%K Labex PRIMES
%K reseau_international
%X Reconstruction of the beating heart in 3D + time in the catheter laboratory using only the available C-arm system would improve diagnosis, guidance, device sizing, and outcome control for intracardiac interventions, e.g., electrophysiology, valvular disease treatment, structural or congenital heart disease. To obtain such a reconstruction, the patient's electrocardiogram (ECG) must be recorded during the acquisition and used in the reconstruction. In this paper, the authors present a 4D reconstruction method aiming to reconstruct the heart from a single sweep 10 s acquisition.The authors introduce the 4D RecOnstructiOn using Spatial and TEmporal Regularization (short 4D ROOSTER) method, which reconstructs all cardiac phases at once, as a 3D + time volume. The algorithm alternates between a reconstruction step based on conjugate gradient and four regularization steps: enforcing positivity, averaging along time outside a motion mask that contains the heart and vessels, 3D spatial total variation minimization, and 1D temporal total variation minimization. 4D ROOSTER recovers the different temporal representations of a moving Shepp and Logan phantom, and outperforms both ECG-gated simultaneous algebraic reconstruction technique and prior image constrained compressed sensing on a clinical case. It generates 3D + time reconstructions with sharp edges which can be used, for example, to estimate the patient's left ventricular ejection fraction.4D ROOSTER can be applied for human cardiac C-arm CT, and potentially in other dynamic tomography areas. It can easily be adapted to other problems as regularization is decoupled from projection and back projection.
%B Med Phys
%V 41
%P 021903
%8 Feb
%U http://www.creatis.insa-lyon.fr/~srit/biblio/mory2014a.pdf
%R 10.1118/1.4860215