Coordinate-Based Neural Representation for Motion-Robust 3D Multiparametric Quantitative MRI with Fat Navigators

Motivation: Multiparametric quantitative MRI is susceptible to potential motion due to the lengthy scan times. Goal(s): To develop a motion-robust multiparametric quantitative mapping technique with fat navigators for neuroimaging. Approach: We developed a multiparametric quantitative MRI sequence integrated with fat navigators. Motion information was extracted from highly-accelerated fat images and incorporated into the reconstruction process. We modeled the quantitative maps as continuous functions of motion-informed coordinates and directly decoded the motion-corrected maps from the corrupted k-space in an unsupervised manner. Results: Our method can yield motion-robust T1, T2, and T2* maps with significantly reduced artifacts. Impact: The proposed method can simultaneously generate motion-robust multiparametric quantitative maps of the whole brain without the need for k-space correction, increasing the clinical usability of multiparametric quantitative MRI.