Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors

Gastrointestinal stromal tumors (GIST) are common mesenchymal tumors, and their effective treatment depends upon the mutational subtype of the <i>KIT/PDGFRA</i> genes. We established deep convolutional neural network (DCNN) models to rapidly predict drug-sensitive mutation subtypes from...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cher-Wei Liang, Pei-Wei Fang, Hsuan-Ying Huang, Chung-Ming Lo
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	gastrointestinal stromal tumor <i>KIT</i> <i>PDGFRA</i> deep convolutional neural network machine learning Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/114e70598c6a4b06a1bc72873254d566
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:114e70598c6a4b06a1bc72873254d566
record_format	dspace
spelling	oai:doaj.org-article:114e70598c6a4b06a1bc72873254d5662021-11-25T17:04:03ZDeep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors10.3390/cancers132257872072-6694https://doaj.org/article/114e70598c6a4b06a1bc72873254d5662021-11-01T00:00:00Zhttps://www.mdpi.com/2072-6694/13/22/5787https://doaj.org/toc/2072-6694Gastrointestinal stromal tumors (GIST) are common mesenchymal tumors, and their effective treatment depends upon the mutational subtype of the <i>KIT/PDGFRA</i> genes. We established deep convolutional neural network (DCNN) models to rapidly predict drug-sensitive mutation subtypes from images of pathological tissue. A total of 5153 pathological images of 365 different GISTs from three different laboratories were collected and divided into training and validation sets. A transfer learning mechanism based on DCNN was used with four different network architectures, to identify cases with drug-sensitive mutations. The accuracy ranged from 87% to 75%. Cross-institutional inconsistency, however, was observed. Using gray-scale images resulted in a 7% drop in accuracy (accuracy 80%, sensitivity 87%, specificity 73%). Using images containing only nuclei (accuracy 81%, sensitivity 87%, specificity 73%) or cytoplasm (accuracy 79%, sensitivity 88%, specificity 67%) produced 6% and 8% drops in accuracy rate, respectively, suggesting buffering effects across subcellular components in DCNN interpretation. The proposed DCNN model successfully inferred cases with drug-sensitive mutations with high accuracy. The contribution of image color and subcellular components was also revealed. These results will help to generate a cheaper and quicker screening method for tumor gene testing.Cher-Wei LiangPei-Wei FangHsuan-Ying HuangChung-Ming LoMDPI AGarticlegastrointestinal stromal tumor<i>KIT</i><i>PDGFRA</i>deep convolutional neural networkmachine learningNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENCancers, Vol 13, Iss 5787, p 5787 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	gastrointestinal stromal tumor <i>KIT</i> <i>PDGFRA</i> deep convolutional neural network machine learning Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	gastrointestinal stromal tumor <i>KIT</i> <i>PDGFRA</i> deep convolutional neural network machine learning Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Cher-Wei Liang Pei-Wei Fang Hsuan-Ying Huang Chung-Ming Lo Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
description	Gastrointestinal stromal tumors (GIST) are common mesenchymal tumors, and their effective treatment depends upon the mutational subtype of the <i>KIT/PDGFRA</i> genes. We established deep convolutional neural network (DCNN) models to rapidly predict drug-sensitive mutation subtypes from images of pathological tissue. A total of 5153 pathological images of 365 different GISTs from three different laboratories were collected and divided into training and validation sets. A transfer learning mechanism based on DCNN was used with four different network architectures, to identify cases with drug-sensitive mutations. The accuracy ranged from 87% to 75%. Cross-institutional inconsistency, however, was observed. Using gray-scale images resulted in a 7% drop in accuracy (accuracy 80%, sensitivity 87%, specificity 73%). Using images containing only nuclei (accuracy 81%, sensitivity 87%, specificity 73%) or cytoplasm (accuracy 79%, sensitivity 88%, specificity 67%) produced 6% and 8% drops in accuracy rate, respectively, suggesting buffering effects across subcellular components in DCNN interpretation. The proposed DCNN model successfully inferred cases with drug-sensitive mutations with high accuracy. The contribution of image color and subcellular components was also revealed. These results will help to generate a cheaper and quicker screening method for tumor gene testing.
format	article
author	Cher-Wei Liang Pei-Wei Fang Hsuan-Ying Huang Chung-Ming Lo
author_facet	Cher-Wei Liang Pei-Wei Fang Hsuan-Ying Huang Chung-Ming Lo
author_sort	Cher-Wei Liang
title	Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
title_short	Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
title_full	Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
title_fullStr	Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
title_full_unstemmed	Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors
title_sort	deep convolutional neural networks detect tumor genotype from pathological tissue images in gastrointestinal stromal tumors
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/114e70598c6a4b06a1bc72873254d566
work_keys_str_mv	AT cherweiliang deepconvolutionalneuralnetworksdetecttumorgenotypefrompathologicaltissueimagesingastrointestinalstromaltumors AT peiweifang deepconvolutionalneuralnetworksdetecttumorgenotypefrompathologicaltissueimagesingastrointestinalstromaltumors AT hsuanyinghuang deepconvolutionalneuralnetworksdetecttumorgenotypefrompathologicaltissueimagesingastrointestinalstromaltumors AT chungminglo deepconvolutionalneuralnetworksdetecttumorgenotypefrompathologicaltissueimagesingastrointestinalstromaltumors
_version_	1718412757726920704

Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors

Ejemplares similares