# Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image Translation

arXiv: https://arxiv.org/abs/2606.17675 · HTML: https://mlsanity.com/paper/2606.17675/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 17 of 17)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models](https://mlsanity.com/paper/2209.12104/) (2022)
- [Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size](https://mlsanity.com/paper/1803.06629/) (2018)
- [Cross-Modality Synthesis from CT to PET using FCN and GAN Networks for Improved Automated Lesion Detection](https://mlsanity.com/paper/1802.07846/) (2018)
- [Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation](https://mlsanity.com/paper/2308.09345/) (2023)
- [VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank](https://mlsanity.com/paper/2406.00125/) (2024)
- [Regression is all you need for medical image translation](https://mlsanity.com/paper/2505.02048/) (2025)
- [Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation](https://mlsanity.com/paper/2507.14575/) (2025)
- [Comparative Analysis of GAN and Diffusion for MRI-to-CT translation](https://mlsanity.com/paper/2509.22049/) (2025)
- [Synthesizing Proton-Density Fat Fraction and R2^* from 2-point Dixon MRI with Generative Machine Learning](https://mlsanity.com/paper/2410.11186/) (2024)

## Abstract (arXiv)

Magnetic resonance imaging-signal fat fraction (MRI-SFF) quantifies tissue fat and serves as an established biomarker for metabolic and musculoskeletal disorders. The acquisition requires, however, specialized MRI sequences, which are not available routinely. We investigate whether SFF can be estimated from widely available T2-weighted (T2w) MRI via image-to-image translation (I2I). We further compare a lightweight 4-level U-Net to a state-of-the-art Denoising Diffusion Probabilistic Model (DDPM) using a dataset of 230 048 paired 2D images (183 517 train, 23 621 val, 22 910 test) from the German National Cohort (NAKO). Both models clearly outperform the identity baseline (Pearson correlation r = 0.769, mean absolute error MAE = 0.070 +/- 0.054), which confirms that the models learn a non-trivial cross-modal mapping. Interestingly, the lightweight U-Net outperforms the DDPM in both correlation (r = 0.975 vs. 0.962) and error (MAE = 0.014 +/- 0.015 vs. 0.019 +/- 0.019), while reducing inference time by a factor of 208 (25.2 ms vs. 5 227.2 ms per image using 50 Denoising Diffusion Implicit Model (DDIM) steps). The strong clinical performance at substantially reduced computational cost enables real-time clinical use.