A generative machine learning approach synthesized PDFF and R2* maps from 2-point Dixon MRIs with significantly greater correlation to ground-truth than conventional voxel-wise baselines.
A generative machine learning approach can accurately synthesize PDFF and R2* maps from fast 2-point Dixon MRI, outperforming conventional voxel-wise methods.
Magnetic Resonance Imaging (MRI) is the gold standard for measuring fat and iron content non-invasively in the body via measures known as Proton Density Fat Fraction (PDFF) and R₂^*, respectively. However, conventional PDFF and R₂^* quantification methods operate on MR images voxel-wise and require at least three measurements to estimate three quantities: water, fat, and R₂^*. Alternatively, the two-point Dixon MRI protocol is widely used and fast because it acquires only two measurements; however, these cannot be used to estimate three quantities voxel-wise. Leveraging the fact that neighboring voxels have similar values, we propose using a generative machine learning approach to learn PDFF and R₂^* from Dixon MRI. We use paired Dixon-IDEAL data from UK Biobank in the liver and a Pix2Pix conditional GAN 1 to demonstrate the first large-scale R₂^* imputation from two-point Dixon MRIs. Using our proposed approach, we synthe-size PDFF and R₂^* maps that show significantly greater correlation with ground-truth than conventional voxel-wise baselines.
Anand et al. (Mon,) conducted a other in Liver fat and iron content. Generative machine learning (Pix2Pix conditional GAN) vs. Conventional voxel-wise baselines was evaluated on Correlation with ground-truth PDFF and R2* maps. A generative machine learning approach synthesized PDFF and R2* maps from 2-point Dixon MRIs with significantly greater correlation to ground-truth than conventional voxel-wise baselines.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: