Cargando…
Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification
In this paper, we present a new deep learning model to classify hematoxylin–eosin-stained breast biopsy images into four classes (normal tissues, benign lesions, in situ carcinomas, and invasive carcinomas). Our model uses a parallel structure consist of a convolutional neural network (CNN) and a re...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6966545/ https://www.ncbi.nlm.nih.gov/pubmed/31795390 http://dx.doi.org/10.3390/cancers11121901 |
_version_ | 1783488760428625920 |
---|---|
author | Yao, Hongdou Zhang, Xuejie Zhou, Xiaobing Liu, Shengyan |
author_facet | Yao, Hongdou Zhang, Xuejie Zhou, Xiaobing Liu, Shengyan |
author_sort | Yao, Hongdou |
collection | PubMed |
description | In this paper, we present a new deep learning model to classify hematoxylin–eosin-stained breast biopsy images into four classes (normal tissues, benign lesions, in situ carcinomas, and invasive carcinomas). Our model uses a parallel structure consist of a convolutional neural network (CNN) and a recurrent neural network (RNN) for image feature extraction, which is greatly different from the common existed serial method of extracting image features by CNN and then inputting them into RNN. Then, we introduce a special perceptron attention mechanism, which is derived from the natural language processing (NLP) field, to unify the features extracted by the two different neural network structures of the model. In the convolution layer, general batch normalization is replaced by the new switchable normalization method. And the latest regularization technology, targeted dropout, is used to substitute for the general dropout in the last three fully connected layers of the model. In the testing phase, we use the model fusion method and test time augmentation technology on three different datasets of hematoxylin–eosin-stained breast biopsy images. The results demonstrate that our model significantly outperforms state-of-the-art methods. |
format | Online Article Text |
id | pubmed-6966545 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-69665452020-01-27 Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification Yao, Hongdou Zhang, Xuejie Zhou, Xiaobing Liu, Shengyan Cancers (Basel) Article In this paper, we present a new deep learning model to classify hematoxylin–eosin-stained breast biopsy images into four classes (normal tissues, benign lesions, in situ carcinomas, and invasive carcinomas). Our model uses a parallel structure consist of a convolutional neural network (CNN) and a recurrent neural network (RNN) for image feature extraction, which is greatly different from the common existed serial method of extracting image features by CNN and then inputting them into RNN. Then, we introduce a special perceptron attention mechanism, which is derived from the natural language processing (NLP) field, to unify the features extracted by the two different neural network structures of the model. In the convolution layer, general batch normalization is replaced by the new switchable normalization method. And the latest regularization technology, targeted dropout, is used to substitute for the general dropout in the last three fully connected layers of the model. In the testing phase, we use the model fusion method and test time augmentation technology on three different datasets of hematoxylin–eosin-stained breast biopsy images. The results demonstrate that our model significantly outperforms state-of-the-art methods. MDPI 2019-11-29 /pmc/articles/PMC6966545/ /pubmed/31795390 http://dx.doi.org/10.3390/cancers11121901 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yao, Hongdou Zhang, Xuejie Zhou, Xiaobing Liu, Shengyan Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title | Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title_full | Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title_fullStr | Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title_full_unstemmed | Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title_short | Parallel Structure Deep Neural Network Using CNN and RNN with an Attention Mechanism for Breast Cancer Histology Image Classification |
title_sort | parallel structure deep neural network using cnn and rnn with an attention mechanism for breast cancer histology image classification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6966545/ https://www.ncbi.nlm.nih.gov/pubmed/31795390 http://dx.doi.org/10.3390/cancers11121901 |
work_keys_str_mv | AT yaohongdou parallelstructuredeepneuralnetworkusingcnnandrnnwithanattentionmechanismforbreastcancerhistologyimageclassification AT zhangxuejie parallelstructuredeepneuralnetworkusingcnnandrnnwithanattentionmechanismforbreastcancerhistologyimageclassification AT zhouxiaobing parallelstructuredeepneuralnetworkusingcnnandrnnwithanattentionmechanismforbreastcancerhistologyimageclassification AT liushengyan parallelstructuredeepneuralnetworkusingcnnandrnnwithanattentionmechanismforbreastcancerhistologyimageclassification |