Conditional Diffusion Models for Semantic 3D Medical Image Synthesis

by   Zolnamar Dorjsembe, et al.
National Taiwan University of Science and Technology
National Taiwan University
The University of Tokyo

This paper introduces Med-DDPM, an innovative solution using diffusion models for semantic 3D medical image synthesis, addressing the prevalent issues in medical imaging such as data scarcity, inconsistent acquisition methods, and privacy concerns. Experimental evidence illustrates that diffusion models surpass Generative Adversarial Networks (GANs) in stability and performance, generating high-quality, realistic 3D medical images. The distinct feature of Med-DDPM is its use of semantic conditioning for the diffusion model in 3D image synthesis. By controlling the generation process through pixel-level mask labels, it facilitates the creation of realistic medical images. Empirical evaluations underscore the superior performance of Med-DDPM over GAN techniques in metrics such as accuracy, stability, and versatility. Furthermore, Med-DDPM outperforms traditional augmentation techniques and synthetic GAN images in enhancing the accuracy of segmentation models. It addresses challenges such as insufficient datasets, lack of annotated data, and class imbalance. Noting the limitations of the Frechet inception distance (FID) metric, we introduce a histogram-equalized FID metric for effective performance evaluation. In summary, Med-DDPM, by utilizing diffusion models, signifies a crucial step forward in the domain of high-resolution semantic 3D medical image synthesis, transcending the limitations of GANs and data constraints. This method paves the way for a promising solution in medical imaging, primarily for data augmentation and anonymization, thus contributing significantly to the field.


page 1

page 5

page 6

page 7


High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks

The ability to generate synthetic medical images is useful for data augm...

ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks

Generative Adversarial Networks (GANs) have shown considerable promise f...

Red-GAN: Attacking class imbalance via conditioned generation. Yet another medical imaging perspective

Exploiting learning algorithms under scarce data regimes is a limitation...

Improving Nonalcoholic Fatty Liver Disease Classification Performance With Latent Diffusion Models

Integrating deep learning with clinical expertise holds great potential ...

Less is More: Unsupervised Mask-guided Annotated CT Image Synthesis with Minimum Manual Segmentations

As a pragmatic data augmentation tool, data synthesis has generally retu...

Unsupervised Medical Image Translation with Adversarial Diffusion Models

Imputation of missing images via source-to-target modality translation c...

Please sign up or login with your details

Forgot password? Click here to reset