DeepFittingNet: A deep neural network‐based approach for simplifying cardiac T1 and T2 estimation with improved robustness

Abstract Purpose To develop and evaluate a deep neural network (DeepFittingNet) for T 1 /T 2 estimation of the most commonly used cardiovascular MR mapping sequences to simplify data processing and improve robustness. Theory and Methods DeepFittingNet is a 1D neural network composed of a recurrent neural network (RNN) and a fully connected (FCNN) neural network, in which RNN adapts to the different number of input signals from various sequences and FCNN subsequently predicts A, B, and T x of a three‐parameter model. DeepFittingNet was trained using Bloch‐equation simulations of MOLLI and saturation‐recovery single‐shot acquisition (SASHA) T 1 mapping sequences, and T 2 ‐prepared balanced SSFP (T 2 ‐prep bSSFP) T 2 mapping sequence, with reference values from the curve‐fitting method. Several imaging confounders were simulated to improve robustness. The trained DeepFittingNet was tested using phantom and in‐vivo signals, and compared to the curve‐fitting algorithm. Results In testing, DeepFittingNet performed T 1 /T 2 estimation of four sequences with improved robustness in inversion‐recovery T 1 estimation. The mean bias in phantom T 1 and T 2 between the curve‐fitting and DeepFittingNet was smaller than 30 and 1 ms, respectively. Excellent agreements between both methods was found in the left ventricle and septum T 1 /T 2 with a mean bias <6 ms. There was no significant difference in the SD of both the left ventricle and septum T 1 /T 2 between the two methods. Conclusion DeepFittingNet trained with simulations of MOLLI, SASHA, and T 2 ‐prep bSSFP performed T 1 /T 2 estimation tasks for all these most used sequences. Compared with the curve‐fitting algorithm, DeepFittingNet improved the robustness for inversion‐recovery T 1 estimation and had comparable performance in terms of accuracy and precision.