logo

Collection of Textures in Colorectal Cancer Histology

Published on: 2016-05-26
DOI: 10.5281/zenodo.53169
Contributors: Kather, Jakob Nikolas; Zöllner, Frank Gerrit; Bianconi, Francesco; Melchers, Susanne M; Schad, Lothar R; Gaiser, Timo; Marx, Alexander; Weis, Cleo-Aron
Datarows: 5,000
images
image-classification

This dataset (Kather_texture_2016_image_tiles_5000) represents a collection of textures in histological images of human colorectal cancer. Dataset contains 5000 histological images of 150 * 150 px each (74 * 74 µm). Each image belongs to exactly one of eight tissue categories. All images are RGB, 0.495 µm per pixel, digitized with an Aperio ScanScope (Aperio/Leica biosystems), magnification 20x.


Histological samples are fully anonymized images of formalin-fixed paraffin-embedded human colorectal adenocarcinomas (primary tumors) from the pathology archive at the Institute of Pathology, University Medical Center Mannheim, Heidelberg University, Mannheim, Germany. Learn more about the dataset here.

License
CC BY 4.0 (see more)