The PatchCamelyon benchmark dataset (PCAM)
Bas Veeling

folder pcam (10 files)
filecamelyonpatch_level_2_split_valid_y.h5.gz 3.04kB
filecamelyonpatch_level_2_split_valid_x.h5.gz 805.97MB
filecamelyonpatch_level_2_split_train_y.h5.gz 21.38kB
filecamelyonpatch_level_2_split_valid_meta.csv 1.85MB
filecamelyonpatch_level_2_split_train_x.h5.gz 6.42GB
filecamelyonpatch_level_2_split_train_mask.h5.gz 14.48MB
filecamelyonpatch_level_2_split_train_meta.csv 15.05MB
filecamelyonpatch_level_2_split_test_y.h5.gz 3.04kB
filecamelyonpatch_level_2_split_test_meta.csv 1.61MB
filecamelyonpatch_level_2_split_test_x.h5.gz 800.88MB
Type: Dataset

title= {The PatchCamelyon benchmark dataset (PCAM)},
keywords= {},
author= {Bas Veeling},
abstract= {The PatchCamelyon benchmark is a new and challenging image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annoted with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than imagenet, trainable on a single GPU.

## Why PCam
Fundamental machine learning advancements are predominantly evaluated on straight-forward natural-image classification datasets. Think MNIST, CIFAR, SVHN. Medical imaging is becoming one of the major applications of ML and we believe it deserves a spot on the list of go-to ML datasets. Both to challenge future work, and to steer developments into directions that are beneficial for this domain.

We think PCam can play a role in this. It packs the clinically-relevant task of metastasis detection into a straight-forward binary image classification task, akin to CIFAR-10 and MNIST. Models can easily be trained on a single GPU in a couple hours, and achieve competitive scores in the Camelyon16 tasks of tumor detection and WSI diagnosis. Furthermore, the balance between task-difficulty and tractability makes it a prime suspect for fundamental machine learning research on topics as active learning, model uncertainty and explainability.
terms= {},
license= {},
superseded= {},
url= {}

Send Feedback