RichardObi/medigan
medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis
This helps radiologists, medical researchers, and AI developers overcome the scarcity of real-world medical imaging data. It takes your request for a specific type of medical image (like mammograms with breast calcifications) and generates realistic, synthetic versions. The output is a dataset of these new images, which can be used to improve the training of AI models for tasks like disease detection or segmentation.
195 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to augment existing medical image datasets or create entirely new ones to train AI models, especially when real patient data is limited or difficult to access.
Not ideal if you need to work exclusively with actual patient data for diagnostic purposes or if your AI model does not benefit from synthetic data.
Stars
195
Forks
22
Language
Python
License
MIT
Category
Last pushed
Jul 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/RichardObi/medigan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
sdv-dev/Copulas
A library to model multivariate data using copulas.
jmtomczak/intro_dgm
"Deep Generative Modeling": Introductory Examples
Mohamedelrefaie/DrivAerNet
A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep...
RiqiangGao/GDP-HMM_AAPMChallenge
The code base for Generalizable Dose Prediction for Heterogenous Multi-Cohort and Multi-Site...
StarLight1212/Generative-models
This project aim to share the knowledge and code concerning generative models, including: GAN,...