lilygeorgescu/MAE-medical-anomaly-detection

Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images

34
/ 100
Emerging

This helps radiologists and medical researchers automatically identify unusual regions in medical images like MRI or CT scans. You provide a collection of 'healthy' scans, and the system learns what normal looks like. It then processes new scans, highlighting areas that deviate from this learned normal structure, outputting an assessment of potential anomalies. This is ideal for medical professionals who need to efficiently screen large volumes of medical imagery for deviations.

No commits in the last 6 months.

Use this if you need to detect anomalies in medical images without having many examples of abnormal cases for training.

Not ideal if you already have a large, labeled dataset of both healthy and abnormal medical images, or if you are not working with medical image data.

medical-imaging radiology-screening diagnostic-support brain-MRI-analysis lung-CT-nodule-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

20

Forks

3

Language

Python

License

Last pushed

Aug 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lilygeorgescu/MAE-medical-anomaly-detection"

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