Existing techniques for 3D MR fingerprinting focus on accelerating either acquisition or template matching, with typically limited spatial resolution. We develop a 3D MRF sequence coupled with a novel end-to-end deep learning image reconstruction framework for rapid and simultaneous whole-brain quantification of T1 and T2 relaxation times with isotropic submillimeter spatial resolution. We demonstrate feasibility with both retrospectively and prospectively accelerated 3D MRF data.
This abstract and the presentation materials are available to members only; a login is required.