FinnBehrendt/patched-Diffusion-Models-UAD

Codebase for Patched Diffusion Models for Unsupervised Anomaly Detection .

32
/ 100
Emerging

This project helps radiologists and medical researchers automatically identify anomalies like tumors or lesions in brain MRI scans. It takes a collection of healthy brain MRI scans as input to learn what a 'normal' brain looks like. It then compares this reference to new MRI scans, highlighting any pixel-level deviations that could indicate a pathology. This tool is for clinicians or researchers working with brain imaging.

No commits in the last 6 months.

Use this if you need to detect abnormalities in brain MRI scans without relying on large, labor-intensive datasets of annotated pathological images.

Not ideal if you require anomaly detection for other anatomical regions or if you prefer a method that doesn't use a patch-based approach, in which case the 'Conditioned Diffusion Models' project from the same authors might be more suitable.

brain-MRI radiology neurology medical-imaging pathology-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

50

Forks

9

Language

Python

License

Last pushed

Mar 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FinnBehrendt/patched-Diffusion-Models-UAD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.