KatherLab/STAMP

Solid Tumor Associative Modeling in Pathology

58
/ 100
Established

This project helps clinical researchers and machine learning engineers analyze large collections of whole-slide histopathology images to discover potential image-based biomarkers. You input digitized tissue slides (gigapixel histopathology images) and patient-level clinical data, and it outputs predictions for patient outcomes (like survival or disease activity scores) along with explainable heatmaps showing important image regions. It's designed for pathologists, oncologists, and data scientists working on computational pathology projects.

115 stars.

Use this if you need an efficient, reproducible workflow to find image-based biomarkers in solid tumor pathology without requiring detailed pixel-level annotations.

Not ideal if your primary goal is pixel-level image segmentation or if you don't work with whole-slide histopathology images.

histopathology oncology biomarker-discovery cancer-research computational-pathology
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

115

Forks

48

Language

Python

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/KatherLab/STAMP"

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