agentdr1/LA_MIL

Implementation of LA_MIL, Local Attention Graph-based Transformer for WSIs, PyTorch

22
/ 100
Experimental

This project helps medical researchers and pathologists analyze large whole slide images (WSIs) of tissue samples to predict genetic alterations or other biomarkers from cancer histology. It takes raw WSI data, processes it into features, and outputs predictions about specific mutations or characteristics present in the tissue. This tool is designed for scientists and clinicians working with digital pathology.

No commits in the last 6 months.

Use this if you need to predict multiple genetic markers or other clinical outcomes directly from whole slide images of cancer tissue, especially if you want to explore different attention mechanisms.

Not ideal if you are not working with whole slide images for biomarker prediction, or if you need a pre-packaged solution that doesn't require setting up a machine learning pipeline.

digital-pathology cancer-research biomarker-prediction histology-analysis medical-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

24

Forks

Language

Python

License

MIT

Last pushed

Oct 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/agentdr1/LA_MIL"

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