Cancer3.AI › AI in Oncology › Datasets › CAMELYON16 / CAMELYON17
Benchmark / challenge Open download CC0

CAMELYON16 / CAMELYON17

The canonical whole-slide benchmark for breast cancer lymph-node metastasis detection; still the first sanity check for any new pathology encoder.

Dataset site { } JSON

At a glance

ProviderRadboud University Medical Center and partners (grand-challenge.org)
AccessOpen download
LicenceCC0
WSIs1 399
Size notesCAMELYON16: 399 slides (270 train / 129 test) with pixel-level metastasis annotations; CAMELYON17: 1,000 slides from 5 centres with patient-level pN stage
FormatsTIFF, CSV
Data typeHistopathology (WSI)
TaskDetectionClassificationSegmentation
CancerInvasive Breast Carcinoma

Labels and annotations

Pixel-level contours of lymph-node metastases (CAMELYON16) drawn by pathologists; slide-level labels and patient pN stage (CAMELYON17).

Details

Not yet documented on this card.

Models trained or evaluated on it

  • evaluation UNI Mahmood Lab, Brigham and Women's Hospital / Harvard Medical School — slide-level metastasis detection benchmark
  • evaluation H-optimus-0 Bioptimus

Sources

  1. CAMELYON17 challenge
  2. Bejnordi BE et al. JAMA 2017 — CAMELYON16 results

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.