Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning

Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endosc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Masayuki Tsuneki, Fahdi Kanavati
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning transfer learning poorly differentiated adenocarcinoma colon Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/1b5830d57b254143bb87e9c22e375d33
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1b5830d57b254143bb87e9c22e375d33
record_format	dspace
spelling	oai:doaj.org-article:1b5830d57b254143bb87e9c22e375d332021-11-25T17:21:22ZDeep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning10.3390/diagnostics111120742075-4418https://doaj.org/article/1b5830d57b254143bb87e9c22e375d332021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/2074https://doaj.org/toc/2075-4418Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endoscopic biopsy specimens is currently the most cost effective method to perform as part of colonoscopic screening in average risk patients, and it is an area that could benefit from AI-based tools to aid pathologists in their clinical workflows. In this study, we trained deep learning models to classify poorly differentiated colorectal ADC from Whole Slide Images (WSIs) using a simple transfer learning method. We evaluated the models on a combination of test sets obtained from five distinct sources, achieving receiver operating characteristic curve (ROC) area under the curves (AUCs) up to 0.95 on 1799 test cases.Masayuki TsunekiFahdi KanavatiMDPI AGarticledeep learningtransfer learningpoorly differentiated adenocarcinomacolonMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 2074, p 2074 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning transfer learning poorly differentiated adenocarcinoma colon Medicine (General) R5-920
spellingShingle	deep learning transfer learning poorly differentiated adenocarcinoma colon Medicine (General) R5-920 Masayuki Tsuneki Fahdi Kanavati Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
description	Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endoscopic biopsy specimens is currently the most cost effective method to perform as part of colonoscopic screening in average risk patients, and it is an area that could benefit from AI-based tools to aid pathologists in their clinical workflows. In this study, we trained deep learning models to classify poorly differentiated colorectal ADC from Whole Slide Images (WSIs) using a simple transfer learning method. We evaluated the models on a combination of test sets obtained from five distinct sources, achieving receiver operating characteristic curve (ROC) area under the curves (AUCs) up to 0.95 on 1799 test cases.
format	article
author	Masayuki Tsuneki Fahdi Kanavati
author_facet	Masayuki Tsuneki Fahdi Kanavati
author_sort	Masayuki Tsuneki
title	Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
title_short	Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
title_full	Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
title_fullStr	Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
title_full_unstemmed	Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning
title_sort	deep learning models for poorly differentiated colorectal adenocarcinoma classification in whole slide images using transfer learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1b5830d57b254143bb87e9c22e375d33
work_keys_str_mv	AT masayukitsuneki deeplearningmodelsforpoorlydifferentiatedcolorectaladenocarcinomaclassificationinwholeslideimagesusingtransferlearning AT fahdikanavati deeplearningmodelsforpoorlydifferentiatedcolorectaladenocarcinomaclassificationinwholeslideimagesusingtransferlearning
_version_	1718412454297337856

Deep Learning Models for Poorly Differentiated Colorectal Adenocarcinoma Classification in Whole Slide Images Using Transfer Learning

Ejemplares similares