mazurowski-lab/medical-image-similarity-metrics
An evaluation framework for image generation metrics.
This framework helps medical researchers and developers evaluate the quality of synthetic medical images by comparing them against real image datasets. You input two folders of medical images—one real and one generated—and it outputs numerical scores indicating how similar their distributions are. This tool is for anyone creating or using AI models that generate medical images and needs to rigorously assess their quality and realism.
No commits in the last 6 months.
Use this if you are a medical imaging researcher or developer who needs to objectively quantify the similarity between a set of synthetically generated medical images and a set of real medical images.
Not ideal if you are looking to compare individual images for pixel-level differences rather than assessing the overall statistical similarity of two image datasets.
Stars
7
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
May 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/mazurowski-lab/medical-image-similarity-metrics"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
RichardObi/medigan
medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis
RiqiangGao/GDP-HMM_AAPMChallenge
The code base for Generalizable Dose Prediction for Heterogenous Multi-Cohort and Multi-Site...