TopoXLab/TopoInteraction

This repository contains the implementation for our work "Learning Topological Interactions for Multi-Class Medical Image Segmentation", accepted to ECCV 2022 (Oral)

33
/ 100
Emerging

This project helps medical imaging specialists refine the output of their segmentation models. It takes segmented medical images (both 2D and 3D) and applies topological rules to improve accuracy, ensuring structures are correctly contained within or excluded from each other. Medical image analysts and researchers can use this to enhance the reliability of their anatomical segmentations.

No commits in the last 6 months.

Use this if you need to enforce specific containment or exclusion relationships between different tissue or organ segments in medical images, like ensuring a tumor is always within a specific organ boundary.

Not ideal if your primary goal is to train a segmentation model from scratch, as this tool is an add-on to existing model training workflows, not a standalone model.

medical-image-segmentation anatomical-analysis biomedical-imaging pathology radiology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

84

Forks

5

Language

Python

License

MIT

Last pushed

Feb 19, 2024

Commits (30d)

0

Get this data via API

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

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