# Synthesizing Proton-Density Fat Fraction and R2^* from 2-point Dixon MRI with Generative Machine Learning

arXiv: https://arxiv.org/abs/2410.11186 · HTML: https://mlsanity.com/paper/2410.11186/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Accelerating Quantitative Susceptibility Mapping using Compressed Sensing and Deep Neural Network](https://mlsanity.com/paper/2103.09375/) (2021)
- [High-fidelity Direct Contrast Synthesis from Magnetic Resonance Fingerprinting](https://mlsanity.com/paper/2212.10817/) (2022)
- [Swap-Free Fat-Water Separation in Dixon MRI using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2107.14175/) (2021)

## Built on by (most cited first, 1 of 1)

- [Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image Translation](https://mlsanity.com/paper/2606.17675/) (2026)

## Abstract (arXiv)

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 to demonstrate the first large-scale R2^* imputation from two-point Dixon MRIs. Using our proposed approach, we synthesize PDFF and R2^* maps that show significantly greater correlation with ground-truth than conventional voxel-wise baselines.