Obtaining accurate segmentations of the heart in real-time MRI allows a more realistic view on clinically relevant parameters, such as the stroke volume. Cardiac real-time MRI can assess diastolic filling under breath maneuvers or other cardiac load situations which potentially enhances diagnostics other than CINE breath hold cardiac MRI. Real-time MRI allows rapid acquisitions during spontaneous breathing, so that it is suited for a wide variety of patients. However, this is a challenging task due to changing heart shapes during contraction and relaxation within a cardiac cycle and heart movement with respiration. In particular, univentricular Fontan hearts are more challenging to detect due to their varying forms. Within this project we support the development of a segmentation pipeline that facilitates the identification of the breathing and heartbeat cycles, thus facilitating the 3D+t reconstruction of the heart from multiple 2D+t real-time sequences.