mazurowski-lab/medical-image-similarity-metrics

An evaluation framework for image generation metrics.

22
/ 100
Experimental

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.

medical imaging image generation radiology AI model evaluation biomedical research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Jupyter Notebook

License

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.