Robust reconstruction of cardiac T1 maps using RNNs

Nicola Martini, Alessio Vatti, Andrea Ripoli, Sara Salaris, Gianmarco Santini, Gabriele Valvano, Maria Filomena Santarelli, Dante Chiappino, Daniele Della Latta

Keywords: RNN, T1 mapping, non-linear fitting, MRI

TL;DR: We propose a Deep Learning technique based on recurrent networks (RNNs) as an alternative method for the reconstruction of parametric maps in cardiac T1 mapping.

Abstract: Cardiac magnetic resonance parametric T1 maps are typically reconstructed using non-linear tting. However this method has limitations due to the high computational cost and robustness. In this study, a recurrent neural network (RNN) is proposed for the robust and fast reconstruction of cardiac T1 maps.

Code Of Conduct: I have read and accept the code of conduct.

Remove If Rejected: Remove submission from public view if paper is rejected.