Deep learning based segmentation of aortic cross sections (2D+t) in multi-vendor 4D PCMRI

Standardized 4D PCMRI postprocessing protocols could enable comparable bloodflow quantification. We propose an automatic segmentation of aortic cross section over time with a residual trained data from different imaging sequences, scanner types, pathologies and position of cross section planes. Dice score, Hausdorff metric as well as flow and velocity curves for the segmented areas show good performance both in the validation and test sets.