Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image Translation
On the map: Diffusion models → Medical imaging and segmentation
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.
Key facts. No citing papers in the map yet (data through 7 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.
Builds on
17 of 37 references.
Closest ancestors · 4
Same direction, newest first
- 2025Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation19 Jul
- 2025Regression is all you need for medical image translation4 May
- 2023Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation18 Aug
- 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey14 Nov
Other references · 13
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017The Perception-Distortion Tradeoffcited by 582
- 2018MedGAN: Medical Image Translation using GANscited by 152
- 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
- 2018Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data sizecited by 42
- 2018Cross-Modality Synthesis from CT to PET using FCN and GAN Networks for Improved Automated Lesion Detectioncited by 29
- 2024VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobankcited by 11
- 2025Comparative Analysis of GAN and Diffusion for MRI-to-CT translationcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024A Physics-based Generative Model to Synthesize Training Datasets for MRI-based Fat Quantification
- 2025Diffusion-Based Synthesis of 3D T1w MPRAGE Images from Multi-Echo GRE with Multi-Parametric MRI Integration
- 2023Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study
- 2023Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
- 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
- 2023FDDM: Unsupervised Medical Image Translation with a Frequency-Decoupled Diffusion Model
- 2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
- 2026Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation