nyukat/GMIC

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

48
/ 100
Emerging

This project provides an AI tool to help radiologists and clinicians interpret high-resolution mammography images for breast cancer screening. You input 16-bit PNG mammograms, and the tool outputs predictions for benign and malignant findings, along with visual 'saliency maps' that highlight specific areas in the image contributing to the prediction. This helps medical professionals quickly identify and understand suspicious regions.

183 stars. No commits in the last 6 months.

Use this if you are a radiologist or clinician seeking to augment your breast cancer screening workflow with an interpretable AI system that provides both classification and visual explanations.

Not ideal if you need a solution for medical imaging types other than mammography or if you require real-time processing in a high-throughput clinical environment without robust IT infrastructure.

radiology breast-cancer-screening medical-imaging diagnostic-support clinical-workflow
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

183

Forks

52

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Jul 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nyukat/GMIC"

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