Deep learning reconstruction for cardiac magnetic resonance fingerprinting T1 and T2 mapping

Purpose To develop a deep learning method for rapidly reconstructing T-1 and T-2 maps from undersampled electrocardiogram (ECG) triggered cardiac magnetic resonance fingerprinting (cMRF) images. Methods A neural network was developed that outputs T-1 and T-2 values when given a measured cMRF signal time course and cardiac RR interval times recorded by an ECG. Over 8 million cMRF signals, corresponding to 4000 random cardiac rhythms, were simulated for training. The training signals were corrupted by simulated k-space undersampling artifacts and random phase shifts to promote robust learning. The deep learning reconstruction was evaluated in Monte Carlo simulations for a variety of cardiac rhythms and compared with dictionary-based pattern matching in 58 healthy subjects at 1.5T. Results In simulations, the normalized root-mean-square error (nRMSE) for T-1 was below 1% in myocardium, blood, and liver for all tested heart rates. For T-2, the nRMSE was below 4% for myocardium and liver and below 6% for blood for all heart rates. The difference in the mean myocardial T-1 or T-2 observed in vivo between dictionary matching and deep learning was 3.6 ms for T-1 and -0.2 ms for T-2. Whereas dictionary generation and pattern matching required more than 4 min per slice, the deep learning reconstruction only required 336 ms. Conclusion A neural network is introduced for reconstructing cMRF T-1 and T-2 maps directly from undersampled spiral images in under 400 ms and is robust to arbitrary cardiac rhythms, which paves the way for rapid online display of cMRF maps.