Cargando…
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...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8673486/ https://www.ncbi.nlm.nih.gov/pubmed/34926274 http://dx.doi.org/10.3389/fonc.2021.769447 |
_version_ | 1784615461187485696 |
---|---|
author | Phan, Nam Nhut Huang, Chi-Cheng Tseng, Ling-Ming Chuang, Eric Y. |
author_facet | Phan, Nam Nhut Huang, Chi-Cheng Tseng, Ling-Ming Chuang, Eric Y. |
author_sort | Phan, Nam Nhut |
collection | PubMed |
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 | Online Article Text |
id | pubmed-8673486 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-86734862021-12-16 Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images Phan, Nam Nhut Huang, Chi-Cheng Tseng, Ling-Ming Chuang, Eric Y. Front Oncol Oncology 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. Frontiers Media S.A. 2021-12-01 /pmc/articles/PMC8673486/ /pubmed/34926274 http://dx.doi.org/10.3389/fonc.2021.769447 Text en Copyright © 2021 Phan, Huang, Tseng and Chuang https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Oncology Phan, Nam Nhut Huang, Chi-Cheng Tseng, Ling-Ming Chuang, Eric Y. Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images |
title | 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_short | 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 |
topic | Oncology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8673486/ https://www.ncbi.nlm.nih.gov/pubmed/34926274 http://dx.doi.org/10.3389/fonc.2021.769447 |
work_keys_str_mv | AT phannamnhut predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT huangchicheng predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT tsenglingming predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages AT chuangericy predictingbreastcancergeneexpressionsignaturebyapplyingdeepconvolutionalneuralnetworksfromunannotatedpathologicalimages |