Suchandrima Banerjee1, Philip James Beatty1, Jian Zhang2, Eric T. Han1, Ajit Shankaranarayanan1
1Applied Science Laboratory, GE Healthcare, San Francisco, CA, United States; 2Electrical Engineering, Stanford University, Palo Alto, CA, United States
Recent trends in MRI have seen an increase in volumetric acquisitions. But three-dimensional (3D) scans are prone to motion artifacts because scan times are often long even after acceleration with parallel imaging and any motion affects the entire volume measurement. Prospective motion correction provides a robust method for suppressing motion artifacts, by tracking patient motion and adjusting scan coordinates to realign with the patient. This work investigates data-driven parallel imaging approaches that account for the k-space transformations associated with prospective motion correction.