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

TL;DR

This paper benchmarks GANs, diffusion models, and flow matching techniques for synthesizing T2-weighted MRI images from T1-weighted scans, finding GANs outperform others in quality and efficiency.

Contribution

It provides a comprehensive comparison of three generative model types for MRI translation, highlighting practical performance differences and guiding future research.

Findings

GANs outperform diffusion and flow matching models in quality and efficiency

Flow models tend to overfit on small datasets and simpler tasks

GAN-based Pix2Pix achieves the best structural fidelity and image quality

Abstract

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 models$\unicode{x2013}$specifically, Generative Adversarial Networks (GANs), diffusion models, and flow matching (FM) techniques$\unicode{x2013}$for 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.