jamesdolezal/biscuit

Bayesian Inference of Slide-level Confidence via Uncertainty Index Thresholding

32
/ 100
Emerging

BISCUIT helps pathology researchers analyze whole-slide images (WSIs) for cancer diagnosis, specifically lung adenocarcinoma vs. squamous cell carcinoma. It takes raw WSI files and outputs classifications with an important confidence score, allowing researchers to distinguish between highly reliable and uncertain predictions. This tool is for pathologists, oncologists, and medical researchers working with digital histopathology images.

No commits in the last 6 months.

Use this if you need to classify whole-slide images for cancer diagnosis and want to know how confident the AI model is in its prediction, allowing you to prioritize cases needing human review.

Not ideal if you are not working with whole-slide pathology images or if you don't need uncertainty quantification for your classification tasks.

digital-histopathology cancer-diagnosis pathology-research medical-imaging oncology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

30

Forks

3

Language

Python

License

Last pushed

Sep 06, 2024

Commits (30d)

0

Get this data via API

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

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