# Diffusion Probabilistic Models beat GANs on Medical Images

arXiv: https://arxiv.org/abs/2212.07501 · HTML: https://mlsanity.com/paper/2212.07501/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [A Morphology Focused Diffusion Probabilistic Model for Synthesis of Histopathology Images](https://mlsanity.com/paper/2209.13167/) (2022)
- [How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?](https://mlsanity.com/paper/1511.06348/) (2015)
- [Generation of Anonymous Chest Radiographs Using Latent Diffusion Models for Training Thoracic Abnormality Classification Systems](https://mlsanity.com/paper/2211.01323/) (2022)
- [GAN-based Data Augmentation for Chest X-ray Classification](https://mlsanity.com/paper/2107.02970/) (2021)

## Built on by (most cited first, 30 of 77)

- [PathLDM: Text conditioned Latent Diffusion Model for Histopathology](https://mlsanity.com/paper/2309.00748/) (2023)
- [Learned representation-guided diffusion models for large-image generation](https://mlsanity.com/paper/2312.07330/) (2023)
- [3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation](https://mlsanity.com/paper/2412.13059/) (2024)
- [Generative quantum machine learning via denoising diffusion probabilistic models](https://mlsanity.com/paper/2310.05866/) (2023)
- [Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2404.04785/) (2024)
- [Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges](https://mlsanity.com/paper/2407.00116/) (2024)
- [Similarity and Quality Metrics for MR Image-To-Image Translation](https://mlsanity.com/paper/2405.08431/) (2024)
- [ZoomLDM: Latent Diffusion Model for multi-scale image generation](https://mlsanity.com/paper/2411.16969/) (2024)
- [PixCell: A generative foundation model for digital histopathology images](https://mlsanity.com/paper/2506.05127/) (2025)
- [A Pragmatic Note on Evaluating Generative Models with Fr'echet Inception Distance for Retinal Image Synthesis](https://mlsanity.com/paper/2502.17160/) (2025)
- [PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions](https://mlsanity.com/paper/2506.23440/) (2025)
- [On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models](https://mlsanity.com/paper/2407.16405/) (2024)
- [Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data](https://mlsanity.com/paper/2508.16783/) (2025)
- [CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model](https://mlsanity.com/paper/2312.01464/) (2023)
- [Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey](https://mlsanity.com/paper/2409.18214/) (2024)
- [Domain-randomized deep learning for neuroimage analysis](https://mlsanity.com/paper/2507.13458/) (2025)
- [Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2312.14976/) (2023)
- [Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields](https://mlsanity.com/paper/2403.17808/) (2024)
- [Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models](https://mlsanity.com/paper/2505.05573/) (2025)
- [RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions](https://mlsanity.com/paper/2505.12887/) (2025)
- [Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion](https://mlsanity.com/paper/2505.20053/) (2025)
- [FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching](https://mlsanity.com/paper/2601.05212/) (2026)
- [Data Augmentation for Environmental Sound Classification Using Diffusion Probabilistic Model with Top-k Selection Discriminator](https://mlsanity.com/paper/2303.15161/) (2023)
- [Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics](https://mlsanity.com/paper/2405.01822/) (2024)
- [LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance](https://mlsanity.com/paper/2510.18446/) (2025)
- [Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology](https://mlsanity.com/paper/2312.09792/) (2023)
- [SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion](https://mlsanity.com/paper/2502.07945/) (2025)
- [Diffusion models applied to skin and oral cancer classification](https://mlsanity.com/paper/2504.00026/) (2025)
- [Diffusion-Based Data Augmentation for Medical Image Segmentation](https://mlsanity.com/paper/2508.17844/) (2025)
- [Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Model](https://mlsanity.com/paper/2509.14780/) (2025)

## Abstract (arXiv)

The success of Deep Learning applications critically depends on the quality and scale of the underlying training data. Generative adversarial networks (GANs) can generate arbitrary large datasets, but diversity and fidelity are limited, which has recently been addressed by denoising diffusion probabilistic models (DDPMs) whose superiority has been demonstrated on natural images. In this study, we propose Medfusion, a conditional latent DDPM for medical images. We compare our DDPM-based model against GAN-based models, which constitute the current state-of-the-art in the medical domain. Medfusion was trained and compared with (i) StyleGan-3 on n=101,442 images from the AIROGS challenge dataset to generate fundoscopies with and without glaucoma, (ii) ProGAN on n=191,027 from the CheXpert dataset to generate radiographs with and without cardiomegaly and (iii) wGAN on n=19,557 images from the CRCMS dataset to generate histopathological images with and without microsatellite stability. In the AIROGS, CRMCS, and CheXpert datasets, Medfusion achieved lower (=better) FID than the GANs (11.63 versus 20.43, 30.03 versus 49.26, and 17.28 versus 84.31). Also, fidelity (precision) and diversity (recall) were higher (=better) for Medfusion in all three datasets. Our study shows that DDPM are a superior alternative to GANs for image synthesis in the medical domain.