Abstract: A computer-implemented method for determining scar segmentation includes receiving a medical image of an object to be segmented acquired after an application of a low-dose of contrast agent, wherein the low-dose of contrast agent comprises less contrast agent than a standard full-dose of contrast agent; and determining a scar segmentation mask by applying a trained artificial neural network to the medical image.

Abstract: A computer-implemented method for determining an orientation of at least one diagnostically relevant sectional plane for heart imaging in a three-dimensional magnetic resonance imaging image dataset, comprises: providing the three-dimensional image dataset; applying a trained function to the three-dimensional image dataset to determine a position of at least one landmark; determining the orientation of the at least one diagnostically relevant sectional plane as a function of at least one landmark; and providing the orientation of the at least one diagnostically relevant sectional plane.

Abstract: The disclosure relates to techniques for determining a motion parameter of a heart. A subset of a sequence of cardiac MR images is applied as a first input to a first trained convolutional neural network configured to determine, as a first output, a probability distribution of at least 2 anatomical landmarks. The sequence of cardiac MR images is cropped and realigned based on the at least 2 anatomical landmarks to determine a reframed and aligned sequence of new cardiac MR images showing the same orientation of the heart. The reframed and aligned sequence of new cardiac MR images is applied to a second trained convolutional neural network configured to determine, as a second output, a further probability distribution of the at least 2 anatomical landmarks in each new MR image of the reframed and aligned sequence, the motion parameter of the heart is determined based on the second output.