# Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

arXiv: https://arxiv.org/abs/2503.00266 · HTML: https://mlsanity.com/paper/2503.00266/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [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)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis](https://mlsanity.com/paper/2305.18453/) (2023)
- [An empirical study on evaluation metrics of generative adversarial networks](https://mlsanity.com/paper/1806.07755/) (2018)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [FlowIE: Efficient Image Enhancement via Rectified Flow](https://mlsanity.com/paper/2406.00508/) (2024)
- [Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation](https://mlsanity.com/paper/2305.05424/) (2023)
- [A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN](https://mlsanity.com/paper/2403.05384/) (2024)
- [Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks](https://mlsanity.com/paper/2403.19880/) (2024)

## Built on by (most cited first, 25 of 25)

- [Flow Matching Meets Biology and Life Science: A Survey](https://mlsanity.com/paper/2507.17731/) (2025)
- [FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching](https://mlsanity.com/paper/2601.05212/) (2026)
- [Benchmarking GANs, Diffusion Models, and Flow Matching for T1w-to-T2w MRI Translation](https://mlsanity.com/paper/2507.14575/) (2025)
- [Scalable next-scale autoregression for medical image generation across anatomical regions](https://mlsanity.com/paper/2602.14512/) (2026)
- [EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis](https://mlsanity.com/paper/2603.13967/) (2026)
- [TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling](https://mlsanity.com/paper/2511.07968/) (2025)
- [Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review](https://mlsanity.com/paper/2510.14462/) (2025)
- [Exploiting Intermediate Reconstructions in Optical Coherence Tomography for Test-Time Adaption of Medical Image Segmentation](https://mlsanity.com/paper/2603.05041/) (2026)
- [Cross Modality Image Translation In Medical Imaging Using Generative Frameworks](https://mlsanity.com/paper/2605.13686/) (2026)
- [WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis](https://mlsanity.com/paper/2606.08670/) (2026)
- [FLAT: FLow-Aligned Training of Unrolled Networks for MRI Reconstruction](https://mlsanity.com/paper/2512.03020/) (2025)
- [Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study](https://mlsanity.com/paper/2603.04340/) (2026)
- [Synthetic Cardiac MRI Image Generation using Deep Generative Models](https://mlsanity.com/paper/2603.24764/) (2026)
- [Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising](https://mlsanity.com/paper/2604.02392/) (2026)
- [Reinforcement learning for inverse silhouette design and rapid laser cutting of compact parallelogram quad kirigami prototypes](https://mlsanity.com/paper/2605.08098/) (2026)
- [VDSB-GWSyn: Diffusion Schr"odinger Bridge for Controllable and Anatomically Feasible Guidewire Synthesis in Coronary Angiography](https://mlsanity.com/paper/2606.00109/) (2026)
- [Learning to Distort: Weakly-Supervised Image Quality Transfer for Prostate DWI Correction](https://mlsanity.com/paper/2606.18869/) (2026)
- [Test-Time Adaptation in Optical Coherence Tomography Using Trajectory-Aligned Time-Independent Flow](https://mlsanity.com/paper/2606.18876/) (2026)
- [VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis](https://mlsanity.com/paper/2608.04557/) (2026)
- [A continually expandable foundation model for brain MRI](https://mlsanity.com/paper/2608.08319/) (2026)
- [ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesis in Scoliosis](https://mlsanity.com/paper/2609.05579/) (2026)
- [Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy](https://mlsanity.com/paper/2609.16690/) (2026)
- [AWR-Net: Decoupling Anatomy and Appearance for 3D Fetal Brain Ultrasound Synthesis](https://mlsanity.com/paper/2609.22635/) (2026)
- [Latent Space Is Not Flat: Rethinking Latent Structure for 3D Medical Image Synthesis](https://mlsanity.com/paper/2609.32794/) (2026)
- [StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching](https://mlsanity.com/paper/2610.15341/) (2026)

## Abstract (arXiv)

Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our method significantly reduces inference time while preserving and further enhancing the quality of the outputs. Furthermore, this approach is highly adaptable, supporting various medical imaging modalities, conditioning mechanisms (such as class labels and masks), and different spatial dimensions, including 2D and 3D. Beyond image generation, it can also be applied to related tasks such as image enhancement. Our results demonstrate the efficiency and versatility of this framework, making it a promising advancement for medical imaging applications. Code with checkpoints and a synthetic dataset (beneficial for classification and segmentation) is now available on: https://github.com/milad1378yz/MOTFM.