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

Abstract

PurposeTo develop and evaluate a deep neural network (DeepFittingNet) for T1/T2 estimation of the most commonly used cardiovascular MR mapping sequences to simplify data processing and improve robustness.Theory and MethodsDeepFittingNet 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 Tx of a three‐parameter model. DeepFittingNet was trained using Bloch‐equation simulations of MOLLI and saturation‐recovery single‐shot acquisition (SASHA) T1 mapping sequences, and T2‐prepared balanced SSFP (T2‐prep bSSFP) T2 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.ResultsIn testing, DeepFittingNet performed T1/T2 estimation of four sequences with improved robustness in inversion‐recovery T1 estimation. The mean bias in phantom T1 and T2 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 T1/T2 with a mean bias <6 ms. There was no significant difference in the SD of both the left ventricle and septum T1/T2 between the two methods.ConclusionDeepFittingNet trained with simulations of MOLLI, SASHA, and T2‐prep bSSFP performed T1/T2 estimation tasks for all these most used sequences. Compared with the curve‐fitting algorithm, DeepFittingNet improved the robustness for inversion‐recovery T1 estimation and had comparable performance in terms of accuracy and precision.

MyoFold: Joint myocardial tissue composition and wall motion quantification via a highly folded sequence

“…A one-dimensional neural network, termed DeepFittingNet, is used to estimate T 1 /T 2 for each pixel. 25 DeepFittingNet consists of a recurrent neural network (RNN) and a fully connected (FCNN) neural network. The RNN, with eight hidden layers, encodes the signals and preparation times.…”

“…A leaky rectified linear unit serves as the activation function for each hidden layer of both RNN and FCNN. 25 The RNN has six input nodes for six hybrid T 1 /T 2 signals; each input node includes three channels for the measured signal S i , TI i , and TEprep i .…”