Fig. 5.

Phantom T₁ maps from two MOLLI sequences (MOLLI5(3)3 and MOLLI4(1)3(1)2) and LL4 with different MyoMapNet models. T₁ difference maps between them were included. All MyoMapNet models show similar map quality, except for the model trained using only post-contrast T₁ mapping data. In the T₁ analysis for the post-contrast models, vials with larger T₁ values (> 900 ms) were excluded. While the model trained using only in-vivo data, phantom data show that the model can reliably estimate T₁ values for vials with T₁/T₂s that are not necessarily well represented in the training dataset