Medical Image Generation
29 papers with code • 5 benchmarks • 4 datasets
Medical image generation is the task of synthesising new medical images.
( Image credit: Towards Adversarial Retinal Image Synthesis )
Benchmarks
These leaderboards are used to track progress in Medical Image Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
ChestX-ray14
ACDC
BCI
Leishmania parasite dataset
Latest papers
Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images
4D medical images, which represent 3D images with temporal information, are crucial in clinical practice for capturing dynamic changes and monitoring long-term disease progression.
Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks
High-quality, large-scale data is essential for robust deep learning models in medical applications, particularly ultrasound image analysis.
WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis
pfriedri/wdm-3d
•
•
Due to the three-dimensional nature of CT- or MR-scans, generative modeling of medical images is a particularly challenging task.
Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models
mazurowski-lab/segmentation-guided-diffusion
•
•
Diffusion models have enabled remarkably high-quality medical image generation, yet it is challenging to enforce anatomical constraints in generated images.
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
mckellwoodland/fid-med-eval
•
•
A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images.
UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN
Experiments on an in-house UWF image dataset demonstrate the superiority of the UWAT-GAN over the state-of-the-art methods.
GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes
ibrahimethemhamamci/generatect
•
•
As an example, we generated 100, 000 3D CT volumes, fivefold the number in our real dataset, and trained the classifier exclusively on these synthetic volumes.
SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation
ubc-tea/sadm-longitudinal-medical-image-generation
•
•
To this end, we propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images.
Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
Furthermore, we demonstrate that synthetic images can be used in a self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (dice score 0. 91 vs. 0. 95 without vs. with synthetic data).
Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
nanboy-ronan/backdoor-fedgan
•
•
In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models.
