Motion-Corrected Deep-Learning Reconstruction Framework for 3D Whole-Heart MRA at 0.55T

Motivation: Short acquisition and reconstruction times are key to adopting novel techniques for 3D cardiac MR angiography (CMRA) in clinical settings. Research on CMRA deep-learning (DL) reconstruction at 0.55T, which could potentially make MRI more affordable, remains limited. Goal(s): To evaluate and adapt a non-rigid motion-corrected model-based DL reconstruction (MoCo-MoDL) for 7-fold accelerated CMRA at 0.55T. Approach: MoCo-MoDL was trained and tested on a dataset of 22 subjects, including healthy subjects and patients, with 7-fold undersampling at 0.55T. Results: The proposed approach could enable 7-fold accelerated 3D whole-heart CMRA at 0.55T with a reconstruction time of 42s, 71x faster than the conventional reconstruction. Impact: The proposed approach validates MoCo-MoDL feasibility at 0.55T, enabling 7-fold undersampled, non-rigid motion-corrected CMRA with 1.36min acquisition and 42s reconstruction, showing promise for clinical implementation in low-field environments and making MRI more attainable and cost-effective.