andreped/NoCodeSeg

🔬 Code-free deep segmentation for computational pathology

42
/ 100
Emerging

This tool helps pathologists and medical researchers automatically identify and outline specific tissue structures like epithelium in whole slide images (WSIs) from biopsies stained with HE and CD3. You provide annotated tissue samples from QuPath, and it trains a deep learning model to accurately segment these structures, outputting predictions that can be viewed and analyzed in real-time in FastPathology or imported back into QuPath. It is designed for histologists and clinical researchers who need to quantify or analyze specific cell types or tissue regions without writing code.

No commits in the last 6 months.

Use this if you need to rapidly train and deploy deep learning models for tissue segmentation on digital pathology slides without extensive programming knowledge, integrating with tools like QuPath and FastPathology.

Not ideal if your primary goal is to perform general image analysis that doesn't involve pathology whole slide images or deep learning segmentation.

digital-pathology histology tissue-segmentation medical-imaging computational-pathology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

56

Forks

16

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 14, 2024

Commits (30d)

0

Get this data via API

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

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