RT Journal Article
SR Electronic
T1 Image-based consensus molecular subtype classification (imCMS) of colorectal cancer using deep learning
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 645143
DO 10.1101/645143
A1 Korsuk Sirinukunwattana
A1 Enric Domingo
A1 Susan Richman
A1 Keara L Redmond
A1 Andrew Blake
A1 Clare Verrill
A1 Simon J Leedham
A1 Aikaterini Chatzipli
A1 Claire Hardy
A1 Celina Whalley
A1 Chieh-Hsi Wu
A1 Andrew D Beggs
A1 Ultan McDermott
A1 Philip Dunne
A1 Angela A Meade
A1 Steven M Walker
A1 Graeme I Murray
A1 Leslie M Samuel
A1 Matthew Seymour
A1 Ian Tomlinson
A1 Philip Quirke
A1 Tim Maughan
A1 Jens Rittscher
A1 Viktor H Koelzer
A1 on behalf of S:CORT consortium
YR 2019
UL http://biorxiv.org/content/early/2019/05/23/645143.abstract
AB 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.