PT  - JOURNAL ARTICLE
AU  - Korsuk Sirinukunwattana
AU  - Enric Domingo
AU  - Susan D Richman
AU  - Keara L Redmond
AU  - Andrew Blake
AU  - Clare Verrill
AU  - Simon J Leedham
AU  - Aikaterini Chatzipli
AU  - Claire Hardy
AU  - Celina M Whalley
AU  - Chieh-hsi Wu
AU  - Andrew D Beggs
AU  - Ultan McDermott
AU  - Philip D Dunne
AU  - Angela Meade
AU  - Steven M Walker
AU  - Graeme I Murray
AU  - Leslie Samuel
AU  - Matthew Seymour
AU  - Ian Tomlinson
AU  - Phil Quirke
AU  - Timothy Maughan
AU  - Jens Rittscher
AU  - Viktor H Koelzer
ED  - ,
TI  - Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning
AID  - 10.1136/gutjnl-2019-319866
DP  - 2021 Mar 01
TA  - Gut
PG  - 544--554
VI  - 70
IP  - 3
4099  - http://gut.bmj.com/content/70/3/544.short
4100  - http://gut.bmj.com/content/70/3/544.full
SO  - Gut2021 Mar 01; 70
AB  - Objective Complex phenotypes captured on histological slides represent the biological processes at play in individual cancers, but the link to underlying molecular classification has not been clarified or systematised. In colorectal cancer (CRC), histological grading is a poor predictor of disease progression, and consensus molecular subtypes (CMSs) cannot be distinguished without gene expression profiling. We hypothesise that image analysis is a cost-effective tool to associate complex features of tissue organisation with molecular and outcome data and to resolve unclassifiable or heterogeneous cases. In this study, we present an image-based approach to predict CRC CMS from standard H&E sections using deep learning.Design Training and evaluation of a neural network were performed using a total of n=1206 tissue sections with comprehensive multi-omic data from three independent datasets (training on FOCUS trial, n=278 patients; test on rectal cancer biopsies, GRAMPIAN cohort, n=144 patients; and The Cancer Genome Atlas (TCGA), n=430 patients). Ground truth CMS calls were ascertained by matching random forest and single sample predictions from CMS classifier.Results Image-based CMS (imCMS) accurately classified slides in unseen datasets from TCGA (n=431 slides, AUC)=0.84) and rectal cancer biopsies (n=265 slides, AUC=0.85). imCMS spatially resolved intratumoural heterogeneity and provided secondary calls correlating with bioinformatic prediction from molecular data. imCMS classified samples previously unclassifiable by RNA expression profiling, reproduced the expected correlations with genomic and epigenetic alterations and showed similar prognostic associations as transcriptomic CMS.Conclusion This study shows that a prediction of RNA expression classifiers can be made from H&E images, opening the door to simple, cheap and reliable biological stratification within routine workflows.