Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Jul 22;5:102. doi: 10.1038/s41746-022-00635-4

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 5 — a Dataset includes different types of images: Catania partition includes biopsies, colorectal polypectomies and a few tissue resections (larger tissue samples), while Radboudumc includes biopsies and few colorectal polypectomies. b The different kind of image leads to a different number of patches per WSI. The upper histogram includes the number of WSIs as a function of the patches that they include, for Catania (red) and Radboudumc (blue). The fact that tissue resections and colorectal polypectomies are larger tissue samples than biopsies lead Catania to have larger images than Radboudumc. The lower histogram includes the number of images/WSIs as a function of the patches that they include, for GlaS (orange), CRC Dataset (yellow), UNITOPATHO (purple), TCGA-COAD (green), Xu dataset (light blue) and AIDA (celestial). c WSIs are scanned with several scanners, leading to heterogeneity in terms of colour. The heterogeneity is evaluated by analyzing the H&E matrices distributions, projected in two dimensions with Principal Component Analysis (PCA). The H&E matrix distributions for patches from training (purple) and testing (magenta) partitions in Catania and Radboudumc data. d The H&E matrix distributions for patches from pathology workflow, from APERIO PT2 (Catania, lime), APERIO PT2 (Catania, sky blue), 3DHistech PANNORAMIC 250 Flash III (Catania, pink), 3DHistech P1000 (Radboudumc, green). e The H&E matrix distributions for patches from private pathology workflow (black) and publicly available datasets (white). f The H&E matrix distributions for patches from GlaS (orange), CRC Dataset (yellow), UNITOPATHO (purple), TCGA-COAD (green), Xu dataset (light blue), AIDA (celestial) and pathology workflow (black).