With rising prevalence of obesity and metabolic syndrome comes an increasing demand of noninvasive detection of nonalcoholic fatty pancreas disease. Chemical shift encoding-based water-fat separation based on a multi-echo gradient echo acquisition enables pancreatic fat fraction (PDFF) mapping. The pancreas is a small organ and requires high spatial resolution which results in prolonged breath-hold duration for PDFF mapping. The present work aims to accelerate high-resolution single-breath-hold pancreas PDFF mapping using a methodology combining sparse sampled acquisitions with compressed sensing and deep learning reconstructions.
This abstract and the presentation materials are available to members only; a login is required.