A Neural Network for Rapid Generation of Cardiac MR Fingerprinting Dictionaries with Arbitrary Heart Rhythms
Jesse Ian Hamilton1, Danielle Currey2, Mark Griswold1,3, and Nicole Seiberlich1,3
1Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States, 2Computer Science, Johns Hopkins University, Baltimore, MD, United States, 3Radiology, University Hospitals, Cleveland, OH, United States
Cardiac MR Fingerprinting with ECG gating typically requires that a new Bloch equation simulation be performed after each scan so that the subject’s cardiac rhythm is incorporated in the dictionary. However, this may be challenging for clinical translation and online reconstruction. This study proposes to use a neural network to rapidly generate the dictionary when given input ranges for T1 and T2, as well as the cardiac rhythm (RR intervals). The network produces dictionaries for arbitrary cardiac rhythms and is more than 100 times faster than performing a Bloch equation simulation.
This abstract and the presentation materials are available to members only;
a login is required.
