Search: onr:"swepub:oai:DiVA.org:liu-162492" >
Quantifying the eff...
-
Tellez, DavidRadboud Univ Nijmegen, Netherlands
(author)
Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
- Article/chapterEnglish2019
Publisher, publication year, extent ...
-
ELSEVIER,2019
-
printrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:liu-162492
-
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-162492URI
-
https://doi.org/10.1016/j.media.2019.101544DOI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:art swepub-publicationtype
Notes
-
Funding Agencies|Radboud Institute of Health Sciences (RIHS), Nijmegen, The NetherlandsNetherlands Government; Dutch Cancer SocietyKWF Kankerbestrijding [KUN 2015-7970]; Alpe dHuZes fund [KUN 2014-7032]; European Unions Horizon 2020 research and innovation programme [825292]
-
Stain variation is a phenomenon observed when distinct pathology laboratories stain tissue slides that exhibit similar but not identical color appearance. Due to this color shift between laboratories, convolutional neural networks (CNNs) trained with images from one lab often underperform on unseen images from the other lab. Several techniques have been proposed to reduce the generalization error, mainly grouped into two categories: stain color augmentation and stain color normalization. The former simulates a wide variety of realistic stain variations during training, producing stain-invariant CNNs. The latter aims to match training and test color distributions in order to reduce stain variation. For the first time, we compared some of these techniques and quantified their effect on CNN classification performance using a heterogeneous dataset of hematoxylin and eosin histopathology images from 4 organs and 9 pathology laboratories. Additionally, we propose a novel unsupervised method to perform stain color normalization using a neural network. Based on our experimental results, we provide practical guidelines on how to use stain color augmentation and stain color normalization in future computational pathology applications. (C) 2019 Elsevier B.V. All rights reserved.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Litjens, GeertRadboud Univ Nijmegen, Netherlands
(author)
-
Bandi, PeterRadboud Univ Nijmegen, Netherlands
(author)
-
Bulten, WouterRadboud Univ Nijmegen, Netherlands
(author)
-
Bokhorst, John-MelleRadboud Univ Nijmegen, Netherlands
(author)
-
Ciompi, FrancescoRadboud Univ Nijmegen, Netherlands
(author)
-
van der Laak, JeroenLinköpings universitet,Avdelningen för radiologiska vetenskaper,Medicinska fakulteten,Centrum för medicinsk bildvetenskap och visualisering, CMIV,Region Östergötland, Klinisk patologi,Radboud Univ Nijmegen, Netherlands(Swepub:liu)jerva26
(author)
-
Radboud Univ Nijmegen, NetherlandsAvdelningen för radiologiska vetenskaper
(creator_code:org_t)
Related titles
-
In:Medical Image Analysis: ELSEVIER581361-84151361-8423
Internet link
Find in a library
To the university's database