Cancer3.AI › AI in Oncology › Datasets › PatchCamelyon (PCam)
Benchmark / challenge Open download CC0

PatchCamelyon (PCam)

Small, fast, fully open patch-classification benchmark — the standard smoke test for image encoders in pathology and a common zero-shot evaluation set.

Dataset site 🤗 1aurent/PatchCamelyon { } JSON
3 508 downloads / month ♥ 12 updated 2024-05-25

At a glance

ProviderVeeling et al.; mirrored on Hugging Face
AccessOpen download
LicenceCC0
96×96 patches327 680
Size notesderived from CAMELYON16; binary label = tumour tissue in the central 32×32 region
Formatsh5ad, PNG, Parquet
Data typeHistopathology (WSI)
TaskClassification
CancerInvasive Breast Carcinoma

Labels and annotations

Binary patch labels derived from CAMELYON16 pixel annotations.

Details

Not yet documented on this card.

Models trained or evaluated on it

Sources

  1. Veeling BS et al. Rotation Equivariant CNNs for Digital Pathology. MICCAI 2018
  2. Hugging Face — 1aurent/PatchCamelyon

This page is educational — it is not medical advice and does not replace consultation with an oncologist. Diagnostic and treatment decisions are made solely by specialist physicians.