# Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation

arXiv: https://arxiv.org/abs/2507.14575 · HTML: https://mlsanity.com/paper/2507.14575/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 19 Jul 2025.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [PnP-Flow: Plug-and-Play Image Restoration with Flow Matching](https://mlsanity.com/paper/2410.02423/) (2024)
- [On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity](https://mlsanity.com/paper/2506.03719/) (2025)
- [LBM: Latent Bridge Matching for Fast Image-to-Image Translation](https://mlsanity.com/paper/2503.07535/) (2025)
- [Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model](https://mlsanity.com/paper/2305.19467/) (2023)
- [Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality](https://mlsanity.com/paper/2503.00266/) (2025)
- [Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images](https://mlsanity.com/paper/2305.07644/) (2023)
- [Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion Model](https://mlsanity.com/paper/2407.05059/) (2024)

## Built on by (most cited first, 4 of 4)

- [CoCoLIT: ControlNet-Conditioned Latent Image Translation for MRI to Amyloid PET Synthesis](https://mlsanity.com/paper/2508.01292/) (2025)
- [Cross Modality Image Translation In Medical Imaging Using Generative Frameworks](https://mlsanity.com/paper/2605.13686/) (2026)
- [Synthetic Cardiac MRI Image Generation using Deep Generative Models](https://mlsanity.com/paper/2603.24764/) (2026)
- [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) enables the acquisition of multiple image contrasts, such as T1-weighted (T1w) and T2-weighted (T2w) scans, each offering distinct diagnostic insights. However, acquiring all desired modalities increases scan time and cost, motivating research into computational methods for cross-modal synthesis. To address this, recent approaches aim to synthesize missing MRI contrasts from those already acquired, reducing acquisition time while preserving diagnostic quality. Image-to-image (I2I) translation provides a promising framework for this task. In this paper, we present a comprehensive benchmark of generative modelsunicodex2013specifically, Generative Adversarial Networks (GANs), diffusion models, and flow matching (FM) techniquesunicodex2013for T1w-to-T2w 2D MRI I2I translation. All frameworks are implemented with comparable settings and evaluated on three publicly available MRI datasets of healthy adults. Our quantitative and qualitative analyses show that the GAN-based Pix2Pix model outperforms diffusion and FM-based methods in terms of structural fidelity, image quality, and computational efficiency. Consistent with existing literature, these results suggest that flow-based models are prone to overfitting on small datasets and simpler tasks, and may require more data to match or surpass GAN performance. These findings offer practical guidance for deploying I2I translation techniques in real-world MRI workflows and highlight promising directions for future research in cross-modal medical image synthesis. Code and models are publicly available at https://github.com/AndreaMoschetto/medical-I2I-benchmark.