Congenital heart defect (CHD) is the primary cause of death in newborns, due to typical complex malformation of the cardiac system. The pulmonary valve and trunk are often a ected and require complex clinical management and in most of the cases surgical or interventional treatment. While minimal invasive methods are emerging, non-invasive imaging-based assessment tools become crucial components in clinical settings. For advanced evaluation and therapy planning purposes, car- diac computed tomography (CT) and cardiac magnetic resonance (CMR) are important non-invasive investigation technique with complementary properties. Although, characterized by high-temporal resolution, CMR does not cover the full motion of the pulmonary trunk. The sparse CMR data acquired in this context include only one 3D scan of the whole heart in the end-diastolic phase and two 2D planes (long and short axes) over the whole cardiac cycle. In this paper we present a cross-modality framework for the evaluation of the pulmonary trunk, which combines the advantages of both, cardiac CT and CMR. A patient-speci c model is estimated from both modalities using hierarchical learning-based tech- niques. The pulmonary trunk model is exploited within a novel dynamic regression-based reconstruction to infer the incomplete CMR temporal information. Extensive experiments performed on 72 cardiac CT and MR sequences demonstrated the average speed of 110 seconds and accuracy of 1.4mm for the proposed approach. To the best of our knowledge this is the rst dynamic model of the pulmonary trunk and right ventricle out ow track estimated from sparse 4D MRI data.     «

Congenital heart defect (CHD) is the primary cause of death in newborns, due to typical complex malformation of the cardiac system. The pulmonary valve and trunk are often a ected and require complex clinical management and in most of the cases surgical or interventional treatment. While minimal invasive methods are emerging, non-invasive imaging-based assessment tools become crucial components in clinical settings. For advanced evaluation and therapy planning purposes, car- diac compute...     »