MICS-Lab/thunder

[NeurIPS25 D&B Spotlight] A tile-level histopathology image understanding benchmark

50
/ 100
Established

This project helps computational pathology researchers and medical AI developers evaluate and compare different foundation models for analyzing histopathology images. You input various foundation models and a diverse collection of cancer histology datasets, and it outputs performance metrics related to downstream task accuracy, feature representations, robustness, and uncertainty. It is designed for those who develop or deploy AI models for digital pathology, allowing them to thoroughly assess model capabilities.

Use this if you need to rigorously compare the performance of different AI foundation models on a wide range of histopathology image analysis tasks and datasets.

Not ideal if you are a clinician looking for a diagnostic tool or a patient seeking medical advice; this is a research and development benchmark.

computational pathology digital pathology cancer research histology image analysis medical AI development
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

43

Forks

11

Language

Python

License

CC-BY-4.0

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MICS-Lab/thunder"

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