junjie-shentu/CXR-IRGen
Implementation of the paper "CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray Image-Report Pairs" (WACV 2024)
This project helps medical AI researchers and developers expand their datasets by generating synthetic chest X-ray images along with corresponding radiology reports. It takes a reference image and associated text embedding, then outputs new, clinically accurate chest X-ray image-report pairs. This tool is for individuals developing deep learning models for medical image analysis, who need to augment their training data.
No commits in the last 6 months.
Use this if you are developing AI models for medical diagnosis from chest X-rays and need to create a larger, more diverse dataset of images and their matching reports for training.
Not ideal if you are a clinician looking for diagnostic support or a patient seeking medical advice; this tool generates synthetic data for research, not clinical use.
Stars
21
Forks
5
Language
Python
License
—
Category
Last pushed
Jul 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/junjie-shentu/CXR-IRGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ge-xing/Diff-UNet
Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation. (using diffusion for 3D...
LemuelPuglisi/BrLP
[MICCAI, 2024] (Oral, RU @ MedIA Best Paper Award) Official implementation of the Brain Latent...
Warvito/generative_chestxray
Repository to train Latent Diffusion Models on Chest X-ray data (MIMIC-CXR) using MONAI...
jwmao1/MedSegFactory
[ICCV 2025] MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs
GabrieleLozupone/LDAE
Official PyTorch implementation of "Latent Diffusion Autoencoders: Toward Efficient and...