Exploiting multiple color representations to improve colon cancer detection in whole slide H&E stains

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

2 Citationer (Scopus)

Abstrakt

Currently, colon cancer diagnosis is based on manual assessment of tissue samples stained with hematoxylin and eosin (H&E). This is a high volume, time consuming, and subjective task which could be aided by automatic cancer detection. We propose an algorithm for automatic cancer detection within WSI H&E stains using a multi class colon tissue classifier based on features extracted from 5 different color representations. Approx. 32000 tissue patches were extracted for the classifier from manual annotations of 9 representative colon tissue types from 74 WSI H&E stains. Colon tissue classifiers based on gray level or color features were trained using leave-one-out forward selection. The best colon tissue classifier was based on color texture features obtaining an average tissue precision-recall (PR) area under the curve (AUC) of 0.886 and a cancer PR-AUC of 0.950 on 20 validation WSI H&E stains.

OriginalsprogEngelsk
TitelComputational Pathology and Ophthalmic Medical Image Analysis : First International Workshop, COMPAY 2018, and 5th International Workshop, OMIA 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 16-20 September 2018, Proceedings
RedaktørerZeike Taylor, Hrvoje Bogunovic, David Snead, Mona K. Garvin, Xin Jan Chen, Francesco Ciompi, Yanwu Xu, Lena Maier-Hein, Mitko Veta, Emanuele Trucco, Danail Stoyanov, Nasir Rajpoot, Jeroen van der Laak, Anne Martel, Stephen McKenna
Antal sider8
ForlagSpringer
Publikationsdato2018
Sider61-68
ISBN (Trykt)978-3-030-00948-9
ISBN (Elektronisk)978-3-030-00949-6
DOI
StatusUdgivet - 2018
Begivenhed1st International Workshop on Computational Pathology, COMPAY 2018, and 5th International Workshop on Ophthalmic Medical Image Analysis, OMIA 2018 - Granada, Spanien
Varighed: 16 okt. 201820 okt. 2018

Konference

Konference1st International Workshop on Computational Pathology, COMPAY 2018, and 5th International Workshop on Ophthalmic Medical Image Analysis, OMIA 2018
LandSpanien
ByGranada
Periode16/10/201820/10/2018
NavnLecture Notes in Computer Science
Vol/bind11039
ISSN0302-9743

    Fingerprint

Citationsformater

Jørgensen, A. S., Emborg, J., Røge, R., & Østergaard, L. R. (2018). Exploiting multiple color representations to improve colon cancer detection in whole slide H&E stains. I Z. Taylor, H. Bogunovic, D. Snead, M. K. Garvin, X. J. Chen, F. Ciompi, Y. Xu, L. Maier-Hein, M. Veta, E. Trucco, D. Stoyanov, N. Rajpoot, J. van der Laak, A. Martel, & S. McKenna (red.), Computational Pathology and Ophthalmic Medical Image Analysis: First International Workshop, COMPAY 2018, and 5th International Workshop, OMIA 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 16-20 September 2018, Proceedings (s. 61-68). Springer. Lecture Notes in Computer Science, Bind. 11039 https://doi.org/10.1007/978-3-030-00949-6_8