Header

UZH-Logo

Maintenance Infos

Image-based consensus molecular subtype classification (imCMS) of colorectal cancer using deep learning


Sirinukunwattana, Korsuk; Domingo, Enric; Richman, Susan; et al; Koelzer, Viktor H (2019). Image-based consensus molecular subtype classification (imCMS) of colorectal cancer using deep learning. bioRxiv.org 645143, University of Zurich.

Abstract

Image analysis is a cost-effective tool to associate complex features of tissue organisation with molecular and outcome data. Here we predict consensus molecular subtypes (CMS) of colorectal cancer (CRC) from standard H&E sections using deep learning. Domain adversarial training of a neural classification network was performed using 1,553 tissue sections with comprehensive multi- omic data from three independent datasets. Image-based consensus molecular subtyping (imCMS) accurately classified CRC whole-slide images and preoperative biopsies, spatially resolved intratumoural heterogeneity and provided accurate secondary calls with higher discriminatory power than bioinformatic prediction. In all three cohorts imCMS established sensible classification in CMS unclassified samples, reproduced expected correlations with (epi)genomic alterations and effectively stratified patients into prognostic subgroups. Leveraging artificial intelligence for the development of novel biomarkers extracted from histological slides with molecular and biological interpretability has remarkable potential for clinical translation.

Abstract

Image analysis is a cost-effective tool to associate complex features of tissue organisation with molecular and outcome data. Here we predict consensus molecular subtypes (CMS) of colorectal cancer (CRC) from standard H&E sections using deep learning. Domain adversarial training of a neural classification network was performed using 1,553 tissue sections with comprehensive multi- omic data from three independent datasets. Image-based consensus molecular subtyping (imCMS) accurately classified CRC whole-slide images and preoperative biopsies, spatially resolved intratumoural heterogeneity and provided accurate secondary calls with higher discriminatory power than bioinformatic prediction. In all three cohorts imCMS established sensible classification in CMS unclassified samples, reproduced expected correlations with (epi)genomic alterations and effectively stratified patients into prognostic subgroups. Leveraging artificial intelligence for the development of novel biomarkers extracted from histological slides with molecular and biological interpretability has remarkable potential for clinical translation.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

81 downloads since deposited on 18 Sep 2019
22 downloads since 12 months
Detailed statistics

Additional indexing

Contributors:S:CORT consortium
Item Type:Working Paper
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Institute of Pathology and Molecular Pathology
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:23 May 2019
Deposited On:18 Sep 2019 14:37
Last Modified:14 Jan 2021 16:06
Series Name:bioRxiv.org
ISSN:2331-8422
Additional Information:Now published in Gut: Sirinukunwattana K, Domingo E, Richman SD, et al: Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning, Gut Published Online First: 20 July 2020. doi: 10.1136/gutjnl-2019-319866
OA Status:Green
Publisher DOI:https://doi.org/10.1101/645143
Official URL:https://www.biorxiv.org/content/biorxiv/early/2019/05/23/645143.full.pdf
Related URLs:https://www.zora.uzh.ch/id/eprint/191057

Download

Green Open Access

Download PDF  'Image-based consensus molecular subtype classification (imCMS) of colorectal cancer using deep learning'.
Preview
Content: Published Version
Filetype: PDF
Size: 4MB
View at publisher
Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)