Torch$T_1$: GPU-accelerated cardiac $T_1$ mapping with deep learning framework

Yi Zhang, Yidong Zhao, Yifeng Shao, Nuno Miguel Ferreira Capitão, Fleur van den Bogert, Qian Tao

Keywords: Quantitative $T1$ mapping, MRI, Automatic differentiation, PyTorch

Abstract: Quantitative cardiac $T_1$ mapping by MRI is an essential non-invasive diagnostic tool for cardiomyopathies. Traditionally, deriving the quantitative $T_1$ maps of myocardial tissue involves solving non-linear parametric fitting problems per image voxel, which is slow with sequential CPU computation and requires analytical derivation of the Jacobian matrix per signal model. In this paper, we introduce a new paradigm of parametric fitting, termed ``Torch$T_1$", which leverages the powerful parallelization of modern GPUs and well-established functionalities of auto-differentiation in the deep learning framework of PyTorch. Torch$T_1$ strictly adheres to the signal model and does not require any training. Our method was evaluated on a $T_1$ mapping dataset with both pre-contrast and post-contrast sequences, and benchmarked by conventional CPU-based fitting and recent end-to-end physics-informed neural network (PINN) mapping. Torch$T_1$ showed more accurate and reliable mapping quality compared with the pretrained PINN, with a 13-fold acceleration compared with the CPU baseline.

Submission Number: 28