Cancer3.AI › AI in Oncology › Datasets › PANDA — Prostate cANcer graDe Assessment
Benchmark / challenge Free registration CC BY-NC-SA 4.0 (Kaggle competition rules)

PANDA — Prostate cANcer graDe Assessment

Reference dataset and challenge for AI Gleason grading; the follow-up Nature Medicine paper validated algorithms on external cohorts.

Dataset site { } JSON

At a glance

ProviderRadboud UMC and Karolinska Institutet (Kaggle challenge)
AccessFree registration
LicenceCC BY-NC-SA 4.0 (Kaggle competition rules)
biopsy WSIs10 616
Size notesthe largest public prostate biopsy set; Gleason / ISUP grade per biopsy from two centres
FormatsTIFF, CSV
Data typeHistopathology (WSI)
TaskClassification
CancerProstate

Labels and annotations

ISUP grade group (1–5) per biopsy; Radboud slides also have region-level Gleason pattern masks.

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 — prostate Gleason grading benchmark

Sources

  1. Bulten W et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat Med 2022
  2. Kaggle — PANDA

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.