Quantitative physiological perfusion parameters can be obtained from dynamic contrast-enhanced (DCE)-MRI. Conventionally, fitting is done with the non-linear least squares (NLLS) approach. However, the NLLS-fit suffers from long processing times and results in noisy parameter maps. In this work, we implemented a physics-informed gated recurrent unit (GRU) network with attention layers for estimating physiological parameters using the extended Tofts model. In simulations, we show it outperforms NLLS with more accurate and precise parameter maps. We show our method produced substantially less noisy parameter maps than NLLS in a fraction of the time in pancreatic cancer patients.
This abstract and the presentation materials are available to members only; a login is required.