Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study

Summary: Background: Determining the status of molecular pathways and key mutations in colorectal cancer is crucial for optimal therapeutic decision making. We therefore aimed to develop a novel deep learning pipeline to predict the status of key molecular pathways and mutations from whole-slide im...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohsin Bilal, PhD, Shan E Ahmed Raza, PhD, Ayesha Azam, MBBS, Simon Graham, PhD, Mohammad Ilyas, ProfPhD, Ian A Cree, ProfPhD, David Snead, ProfMBBS, Fayyaz Minhas, PhD, Nasir M Rajpoot, ProfPhD
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/868e1cf7610949dda0fc3e4b9bfb3b3f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:868e1cf7610949dda0fc3e4b9bfb3b3f
record_format	dspace
spelling	oai:doaj.org-article:868e1cf7610949dda0fc3e4b9bfb3b3f2021-11-24T04:33:24ZDevelopment and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study2589-750010.1016/S2589-7500(21)00180-1https://doaj.org/article/868e1cf7610949dda0fc3e4b9bfb3b3f2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2589750021001801https://doaj.org/toc/2589-7500Summary: Background: Determining the status of molecular pathways and key mutations in colorectal cancer is crucial for optimal therapeutic decision making. We therefore aimed to develop a novel deep learning pipeline to predict the status of key molecular pathways and mutations from whole-slide images of haematoxylin and eosin-stained colorectal cancer slides as an alternative to current tests. Methods: In this retrospective study, we used 502 diagnostic slides of primary colorectal tumours from 499 patients in The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) cohort and developed a weakly supervised deep learning framework involving three separate convolutional neural network models. Whole-slide images were divided into equally sized tiles and model 1 (ResNet18) extracted tumour tiles from non-tumour tiles. These tumour tiles were inputted into model 2 (adapted ResNet34), trained by iterative draw and rank sampling to calculate a prediction score for each tile that represented the likelihood of a tile belonging to the molecular labels of high mutation density (vs low mutation density), microsatellite instability (vs microsatellite stability), chromosomal instability (vs genomic stability), CpG island methylator phenotype (CIMP)-high (vs CIMP-low), BRAFmut (vs BRAFWT), TP53mut (vs TP53WT), and KRASWT (vs KRASmut). These scores were used to identify the top-ranked titles from each slide, and model 3 (HoVer-Net) segmented and classified the different types of cell nuclei in these tiles. We calculated the area under the convex hull of the receiver operating characteristic curve (AUROC) as a model performance measure and compared our results with those of previously published methods. Findings: Our iterative draw and rank sampling method yielded mean AUROCs for the prediction of hypermutation (0·81 [SD 0·03] vs 0·71), microsatellite instability (0·86 [0·04] vs 0·74), chromosomal instability (0·83 [0·02] vs 0·73), BRAFmut (0·79 [0·01] vs 0·66), and TP53mut (0·73 [0·02] vs 0·64) in the TCGA-CRC-DX cohort that were higher than those from previously published methods, and an AUROC for KRASmut that was similar to previously reported methods (0·60 [SD 0·04] vs 0·60). Mean AUROC for predicting CIMP-high status was 0·79 (SD 0·05). We found high proportions of tumour-infiltrating lymphocytes and necrotic tumour cells to be associated with microsatellite instability, and high proportions of tumour-infiltrating lymphocytes and a low proportion of necrotic tumour cells to be associated with hypermutation. Interpretation: After large-scale validation, our proposed algorithm for predicting clinically important mutations and molecular pathways, such as microsatellite instability, in colorectal cancer could be used to stratify patients for targeted therapies with potentially lower costs and quicker turnaround times than sequencing-based or immunohistochemistry-based approaches. Funding: The UK Medical Research Council.Mohsin Bilal, PhDShan E Ahmed Raza, PhDAyesha Azam, MBBSSimon Graham, PhDMohammad Ilyas, ProfPhDIan A Cree, ProfPhDDavid Snead, ProfMBBSFayyaz Minhas, PhDNasir M Rajpoot, ProfPhDElsevierarticleComputer applications to medicine. Medical informaticsR858-859.7ENThe Lancet: Digital Health, Vol 3, Iss 12, Pp e763-e772 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Mohsin Bilal, PhD Shan E Ahmed Raza, PhD Ayesha Azam, MBBS Simon Graham, PhD Mohammad Ilyas, ProfPhD Ian A Cree, ProfPhD David Snead, ProfMBBS Fayyaz Minhas, PhD Nasir M Rajpoot, ProfPhD Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
description	Summary: Background: Determining the status of molecular pathways and key mutations in colorectal cancer is crucial for optimal therapeutic decision making. We therefore aimed to develop a novel deep learning pipeline to predict the status of key molecular pathways and mutations from whole-slide images of haematoxylin and eosin-stained colorectal cancer slides as an alternative to current tests. Methods: In this retrospective study, we used 502 diagnostic slides of primary colorectal tumours from 499 patients in The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) cohort and developed a weakly supervised deep learning framework involving three separate convolutional neural network models. Whole-slide images were divided into equally sized tiles and model 1 (ResNet18) extracted tumour tiles from non-tumour tiles. These tumour tiles were inputted into model 2 (adapted ResNet34), trained by iterative draw and rank sampling to calculate a prediction score for each tile that represented the likelihood of a tile belonging to the molecular labels of high mutation density (vs low mutation density), microsatellite instability (vs microsatellite stability), chromosomal instability (vs genomic stability), CpG island methylator phenotype (CIMP)-high (vs CIMP-low), BRAFmut (vs BRAFWT), TP53mut (vs TP53WT), and KRASWT (vs KRASmut). These scores were used to identify the top-ranked titles from each slide, and model 3 (HoVer-Net) segmented and classified the different types of cell nuclei in these tiles. We calculated the area under the convex hull of the receiver operating characteristic curve (AUROC) as a model performance measure and compared our results with those of previously published methods. Findings: Our iterative draw and rank sampling method yielded mean AUROCs for the prediction of hypermutation (0·81 [SD 0·03] vs 0·71), microsatellite instability (0·86 [0·04] vs 0·74), chromosomal instability (0·83 [0·02] vs 0·73), BRAFmut (0·79 [0·01] vs 0·66), and TP53mut (0·73 [0·02] vs 0·64) in the TCGA-CRC-DX cohort that were higher than those from previously published methods, and an AUROC for KRASmut that was similar to previously reported methods (0·60 [SD 0·04] vs 0·60). Mean AUROC for predicting CIMP-high status was 0·79 (SD 0·05). We found high proportions of tumour-infiltrating lymphocytes and necrotic tumour cells to be associated with microsatellite instability, and high proportions of tumour-infiltrating lymphocytes and a low proportion of necrotic tumour cells to be associated with hypermutation. Interpretation: After large-scale validation, our proposed algorithm for predicting clinically important mutations and molecular pathways, such as microsatellite instability, in colorectal cancer could be used to stratify patients for targeted therapies with potentially lower costs and quicker turnaround times than sequencing-based or immunohistochemistry-based approaches. Funding: The UK Medical Research Council.
format	article
author	Mohsin Bilal, PhD Shan E Ahmed Raza, PhD Ayesha Azam, MBBS Simon Graham, PhD Mohammad Ilyas, ProfPhD Ian A Cree, ProfPhD David Snead, ProfMBBS Fayyaz Minhas, PhD Nasir M Rajpoot, ProfPhD
author_facet	Mohsin Bilal, PhD Shan E Ahmed Raza, PhD Ayesha Azam, MBBS Simon Graham, PhD Mohammad Ilyas, ProfPhD Ian A Cree, ProfPhD David Snead, ProfMBBS Fayyaz Minhas, PhD Nasir M Rajpoot, ProfPhD
author_sort	Mohsin Bilal, PhD
title	Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
title_short	Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
title_full	Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
title_fullStr	Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
title_full_unstemmed	Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
title_sort	development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/868e1cf7610949dda0fc3e4b9bfb3b3f
work_keys_str_mv	AT mohsinbilalphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT shaneahmedrazaphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT ayeshaazammbbs developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT simongrahamphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT mohammadilyasprofphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT ianacreeprofphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT davidsneadprofmbbs developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT fayyazminhasphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy AT nasirmrajpootprofphd developmentandvalidationofaweaklysuperviseddeeplearningframeworktopredictthestatusofmolecularpathwaysandkeymutationsincolorectalcancerfromroutinehistologyimagesaretrospectivestudy
_version_	1718415988675837952

Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study

Ejemplares similares