Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods

Abstract Tissue microarray (TMA) core images are a treasure trove for artificial intelligence applications. However, a common problem of TMAs is multiple sectioning, which can change the content of the intended tissue core and requires re-labelling. Here, we investigate different ensemble methods fo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Huu-Giao Nguyen, Annika Blank, Heather E. Dawson, Alessandro Lugli, Inti Zlobec
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b59e9d18919b4f2499e27497bb7e8341
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b59e9d18919b4f2499e27497bb7e8341
record_format	dspace
spelling	oai:doaj.org-article:b59e9d18919b4f2499e27497bb7e83412021-12-02T13:57:37ZClassification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods10.1038/s41598-021-81352-y2045-2322https://doaj.org/article/b59e9d18919b4f2499e27497bb7e83412021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81352-yhttps://doaj.org/toc/2045-2322Abstract Tissue microarray (TMA) core images are a treasure trove for artificial intelligence applications. However, a common problem of TMAs is multiple sectioning, which can change the content of the intended tissue core and requires re-labelling. Here, we investigate different ensemble methods for colorectal tissue classification using high-throughput TMAs. Hematoxylin and Eosin (H&E) core images of 0.6 mm or 1.0 mm diameter from three international cohorts were extracted from 54 digital slides (n = 15,150 cores). After TMA core extraction and color enhancement, five different flows of independent and ensemble deep learning were applied. Training and testing data with 2144 and 13,006 cores included three classes: tumor, normal or “other” tissue. Ground-truth data were collected from 30 ngTMA slides (n = 8689 cores). A test augmentation is applied to reduce the uncertain prediction. Predictive accuracy of the best method, namely Soft Voting Ensemble of one VGG and one CapsNet models was 0.982, 0.947 and 0.939 for normal, “other” and tumor, which outperformed to independent or ensemble learning with one base-estimator. Our high-accuracy algorithm for colorectal tissue classification in high-throughput TMAs is amenable to images from different institutions, core sizes and stain intensity. It helps to reduce error in TMA core evaluations with previously given labels.Huu-Giao NguyenAnnika BlankHeather E. DawsonAlessandro LugliInti ZlobecNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Huu-Giao Nguyen Annika Blank Heather E. Dawson Alessandro Lugli Inti Zlobec Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
description	Abstract Tissue microarray (TMA) core images are a treasure trove for artificial intelligence applications. However, a common problem of TMAs is multiple sectioning, which can change the content of the intended tissue core and requires re-labelling. Here, we investigate different ensemble methods for colorectal tissue classification using high-throughput TMAs. Hematoxylin and Eosin (H&E) core images of 0.6 mm or 1.0 mm diameter from three international cohorts were extracted from 54 digital slides (n = 15,150 cores). After TMA core extraction and color enhancement, five different flows of independent and ensemble deep learning were applied. Training and testing data with 2144 and 13,006 cores included three classes: tumor, normal or “other” tissue. Ground-truth data were collected from 30 ngTMA slides (n = 8689 cores). A test augmentation is applied to reduce the uncertain prediction. Predictive accuracy of the best method, namely Soft Voting Ensemble of one VGG and one CapsNet models was 0.982, 0.947 and 0.939 for normal, “other” and tumor, which outperformed to independent or ensemble learning with one base-estimator. Our high-accuracy algorithm for colorectal tissue classification in high-throughput TMAs is amenable to images from different institutions, core sizes and stain intensity. It helps to reduce error in TMA core evaluations with previously given labels.
format	article
author	Huu-Giao Nguyen Annika Blank Heather E. Dawson Alessandro Lugli Inti Zlobec
author_facet	Huu-Giao Nguyen Annika Blank Heather E. Dawson Alessandro Lugli Inti Zlobec
author_sort	Huu-Giao Nguyen
title	Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
title_short	Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
title_full	Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
title_fullStr	Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
title_full_unstemmed	Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
title_sort	classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b59e9d18919b4f2499e27497bb7e8341
work_keys_str_mv	AT huugiaonguyen classificationofcolorectaltissueimagesfromhighthroughputtissuemicroarraysbyensembledeeplearningmethods AT annikablank classificationofcolorectaltissueimagesfromhighthroughputtissuemicroarraysbyensembledeeplearningmethods AT heatheredawson classificationofcolorectaltissueimagesfromhighthroughputtissuemicroarraysbyensembledeeplearningmethods AT alessandrolugli classificationofcolorectaltissueimagesfromhighthroughputtissuemicroarraysbyensembledeeplearningmethods AT intizlobec classificationofcolorectaltissueimagesfromhighthroughputtissuemicroarraysbyensembledeeplearningmethods
_version_	1718392282208534528

Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods

Ejemplares similares