Multi-contrast mri image reconstruction using machine learning

A computer configured for reconstructing an MRI image, the computer comprising:

• a memory storing executable instructions;
• an interface;
• and
• a processor configured to execute the instructions to cause the computer to:
• receive, by the interface, a plurality of MRI measurement data sets f1 to fN, wherein each data set is acquired from an examination object based on a different MRI protocol of an MRI system;
• receive, by the interface, MRI images u10 to uN0 corresponding to the MRI measurement data sets f1 to fN;
• and
• in at least a first step GD1:
• perform, by the processor, one or more translation and rotation transformations on the MRI images u10 to uN0;
• apply, by the processor, one or more trained functions:
• to the transformed MRI images u10 to uN0, using a neural network, and to the MRI images u10 to uN0, using a forward-sampling operator;
• perform, by the processor, one or more inverse translation and rotation transformations on an output of the neural network;
• generate, by the processor, at least one output MRI image uT based on an output of the forward-sampling operator, the inversely transformed output of the neural network, and the input MRI images u10 to uN0;
• and
• provide, by the interface, the at least one output MRI image uT.