Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images

We proposed a highly versatile two-step transfer learning pipeline for predicting the gene signature defining the intrinsic breast cancer subtypes using unannotated pathological images. Deciphering breast cancer molecular subtypes by deep learning approaches could provide a convenient and efficient...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nam Nhut Phan, Chi-Cheng Huang, Ling-Ming Tseng, Eric Y. Chuang
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	deep learning convolutional neural networks breast cancer intrinsic subtypes pathology whole slide image PAM50 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/5fd822eabb5f4ec8b5c3953244c24d43
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5fd822eabb5f4ec8b5c3953244c24d43
record_format	dspace
spelling	oai:doaj.org-article:5fd822eabb5f4ec8b5c3953244c24d432021-12-01T22:31:09ZPredicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images2234-943X10.3389/fonc.2021.769447https://doaj.org/article/5fd822eabb5f4ec8b5c3953244c24d432021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fonc.2021.769447/fullhttps://doaj.org/toc/2234-943XWe proposed a highly versatile two-step transfer learning pipeline for predicting the gene signature defining the intrinsic breast cancer subtypes using unannotated pathological images. Deciphering breast cancer molecular subtypes by deep learning approaches could provide a convenient and efficient method for the diagnosis of breast cancer patients. It could reduce costs associated with transcriptional profiling and subtyping discrepancy between IHC assays and mRNA expression. Four pretrained models such as VGG16, ResNet50, ResNet101, and Xception were trained with our in-house pathological images from breast cancer patient with recurrent status in the first transfer learning step and TCGA-BRCA dataset for the second transfer learning step. Furthermore, we also trained ResNet101 model with weight from ImageNet for comparison to the aforementioned models. The two-step deep learning models showed promising classification results of the four breast cancer intrinsic subtypes with accuracy ranging from 0.68 (ResNet50) to 0.78 (ResNet101) in both validation and testing sets. Additionally, the overall accuracy of slide-wise prediction showed even higher average accuracy of 0.913 with ResNet101 model. The micro- and macro-average area under the curve (AUC) for these models ranged from 0.88 (ResNet50) to 0.94 (ResNet101), whereas ResNet101_imgnet weighted with ImageNet archived an AUC of 0.92. We also show the deep learning model prediction performance is significantly improved relatively to the common Genefu tool for breast cancer classification. Our study demonstrated the capability of deep learning models to classify breast cancer intrinsic subtypes without the region of interest annotation, which will facilitate the clinical applicability of the proposed models.Nam Nhut PhanNam Nhut PhanNam Nhut PhanChi-Cheng HuangChi-Cheng HuangLing-Ming TsengLing-Ming TsengEric Y. ChuangEric Y. ChuangEric Y. ChuangFrontiers Media S.A.articledeep learningconvolutional neural networksbreast cancer intrinsic subtypespathologywhole slide imagePAM50Neoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENFrontiers in Oncology, Vol 11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning convolutional neural networks breast cancer intrinsic subtypes pathology whole slide image PAM50 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	deep learning convolutional neural networks breast cancer intrinsic subtypes pathology whole slide image PAM50 Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Nam Nhut Phan Nam Nhut Phan Nam Nhut Phan Chi-Cheng Huang Chi-Cheng Huang Ling-Ming Tseng Ling-Ming Tseng Eric Y. Chuang Eric Y. Chuang Eric Y. Chuang Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
description	We proposed a highly versatile two-step transfer learning pipeline for predicting the gene signature defining the intrinsic breast cancer subtypes using unannotated pathological images. Deciphering breast cancer molecular subtypes by deep learning approaches could provide a convenient and efficient method for the diagnosis of breast cancer patients. It could reduce costs associated with transcriptional profiling and subtyping discrepancy between IHC assays and mRNA expression. Four pretrained models such as VGG16, ResNet50, ResNet101, and Xception were trained with our in-house pathological images from breast cancer patient with recurrent status in the first transfer learning step and TCGA-BRCA dataset for the second transfer learning step. Furthermore, we also trained ResNet101 model with weight from ImageNet for comparison to the aforementioned models. The two-step deep learning models showed promising classification results of the four breast cancer intrinsic subtypes with accuracy ranging from 0.68 (ResNet50) to 0.78 (ResNet101) in both validation and testing sets. Additionally, the overall accuracy of slide-wise prediction showed even higher average accuracy of 0.913 with ResNet101 model. The micro- and macro-average area under the curve (AUC) for these models ranged from 0.88 (ResNet50) to 0.94 (ResNet101), whereas ResNet101_imgnet weighted with ImageNet archived an AUC of 0.92. We also show the deep learning model prediction performance is significantly improved relatively to the common Genefu tool for breast cancer classification. Our study demonstrated the capability of deep learning models to classify breast cancer intrinsic subtypes without the region of interest annotation, which will facilitate the clinical applicability of the proposed models.
format	article
author	Nam Nhut Phan Nam Nhut Phan Nam Nhut Phan Chi-Cheng Huang Chi-Cheng Huang Ling-Ming Tseng Ling-Ming Tseng Eric Y. Chuang Eric Y. Chuang Eric Y. Chuang
author_facet	Nam Nhut Phan Nam Nhut Phan Nam Nhut Phan Chi-Cheng Huang Chi-Cheng Huang Ling-Ming Tseng Ling-Ming Tseng Eric Y. Chuang Eric Y. Chuang Eric Y. Chuang
author_sort	Nam Nhut Phan
title	Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
title_short	Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
title_full	Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
title_fullStr	Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
title_full_unstemmed	Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images
title_sort	predicting breast cancer gene expression signature by applying deep convolutional neural networks from unannotated pathological images
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/5fd822eabb5f4ec8b5c3953244c24d43
work_keys_str_mv	AT namnhutphan predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT namnhutphan predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT namnhutphan predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT chichenghuang predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT chichenghuang predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT lingmingtseng predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT lingmingtseng predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT ericychuang predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT ericychuang predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT ericychuang predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages
_version_	1718404102718750720

Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images

Ejemplares similares