Systems and methods for cine magnetic resonance fingerprinting

A method for cine magnetic resonance fingerprinting (MRF), comprising:

• obtaining k-space data of an MRF scan of a subject, the k-space data acquired over a plurality of phases of at least one cardiac cycle of the subject;
• training an image reconstruction network (IRN) to output, for each phase of the plurality of phases, one or more subspace images of the subject using the k-space data, the training of the IRN comprising:
• sorting the k-space data into a plurality of bins to form sorted k-space data, each bin corresponding to a respective phase of the plurality of phases, based on an electrocardiogram (ECG) signal of the subject;
• preparing a plurality of input tensors by generating a first input tensor comprising a first matrix of random values, generating a last input tensor comprising a last matrix of random values, and performing a linear interpolation between the first matrix of random values and the last matrix of random values to generate a plurality of intermediate input tensors, the plurality of input tensors comprising the first input tensor, the plurality of intermediate input tensors, and the last input tensor, and wherein each input tensor of the plurality of input tensors corresponds to a respective phase of the plurality of phases;
• and
• training the IRN to output, for each phase of the plurality of phases, the one or more subspace images of the subject using the sorted k-space data and the plurality of input tensors;
• training a parameter estimation network (PEN) to output, for each phase of the plurality of phases, a set of tissue parameter maps of the subject using the one or more subspace images output by the IRN for that phase;
• upon training the IRN and the PEN, obtaining, using the trained IRN and the trained PEN, a final set of tissue parameter maps of the subject for one or more or each of the plurality of phases;
• and
• displaying and/or saving in memory the final set of tissue parameter maps for the one or more or each of the plurality of phases.