Abstract
BACKGROUND: Image reconstruction from highly undersampled four-dimensional (4D) flow magnetic resonance imaging (MRI) data can be very time-consuming and may result in significant underestimation of velocities depending on regularization, thereby limiting the applicability of the method. The objective of the present work was to develop a generalizable self-supervised deep learning-based framework for fast and accurate reconstruction of highly undersampled 4D flow MRI and to demonstrate the utility of the framework for aortic and cerebrovascular applications. METHODS: The proposed deep-learning-based framework, called FlowMRI-Net, employs physics-driven unrolled optimization using a complex-valued convolutional recurrent neural network and is trained in a self-supervised manner. The generalizability of the framework is evaluated using aortic and cerebrovascular 4D flow MRI acquisitions acquired on systems from two different vendors for various undersampling factors (R = 8, 16, 24) and compared to compressed sensing locally low rank (CS-LLR) reconstructions. Evaluation includes an ablation study and a qualitative and quantitative analysis of image and velocity magnitudes. RESULTS: FlowMRI-Net outperforms CS-LLR for aortic 4D flow MRI reconstruction, resulting in significantly lower vectorial normalized root mean square error and mean directional errors for velocities in the thoracic aorta. Furthermore, the feasibility of FlowMRI-Net's generalizability is demonstrated for cerebrovascular 4D flow MRI reconstruction. Reconstruction times ranged from 3 to 7 min on commodity central processing unit/graphical processing unit hardware. CONCLUSION: FlowMRI-Net enables fast and accurate reconstruction of highly undersampled aortic and cerebrovascular 4D flow MRI, with possible applications to other vascular territories.