Huster-Hq/MonoBox

[AAAI 2025] MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint

25
/ 100
Experimental

This project helps medical image analysts and endoscopists accurately identify polyps in colonoscopy images, even when initial bounding box annotations are imprecise. It takes medical images with rough box outlines of polyps and generates precise pixel-level segmentations. The primary users are researchers and practitioners involved in medical image analysis and disease detection.

Use this if you need to perform highly accurate polyp segmentation from medical images and your bounding box annotations are often not perfectly tight around the polyp.

Not ideal if your primary goal is to segment very small, thin, or partially obscured objects outside of the medical domain, as it may struggle with these cases.

polyp-segmentation medical-imaging endoscopy-analysis biomedical-annotation diagnostic-imaging
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

Last pushed

Dec 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Huster-Hq/MonoBox"

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