DIAGNijmegen/pathology-whole-slide-data

A package for working with whole-slide data including a fast batch iterator that can be used to train deep learning models.

51
/ 100
Established

This tool helps pathologists and researchers working with digital microscopy to efficiently prepare whole-slide images and their annotations for analysis. It takes high-resolution whole-slide image files (like .tif) and associated annotations (from software like ASAP or QuPath) as input. It then rapidly extracts specific regions of interest, known as patches, and their corresponding labels, which are outputted for use in training deep learning models or similar analyses.

112 stars.

Use this if you need to quickly and efficiently sample specific regions (patches) from large whole-slide pathology images and their associated annotations, especially for training AI models, without having to save all patches to disk beforehand.

Not ideal if you primarily need to view or manually analyze whole-slide images and annotations, rather than programmatically extract patches for computational tasks.

digital-pathology histopathology-imaging medical-image-analysis cancer-research diagnostic-imaging
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

112

Forks

31

Language

Python

License

Apache-2.0

Last pushed

Nov 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DIAGNijmegen/pathology-whole-slide-data"

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