A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification

Rui Yan; Fei Ren; Zihao Wang; Lihua Wang; Yubo Ren; Yudong Liu; Xiaosong Rao; Chunhou Zheng; Fa Zhang

doi:10.1109/BIBM.2018.8621429

A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification

Rui Yan
, Fei Ren
, Zihao Wang
, Lihua Wang
, Yubo Ren
, Yudong Liu
, Xiaosong Rao
, Chunhou Zheng
, Fa Zhang^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

26 Citations (Scopus)

Abstract

Hematoxylin and Eosin HE stained breast tissue samples from biopsies are observed under microscopy for the gold standard diagnosis of breast cancer. However, a substantial workload increases and the complexity of the pathological images make this task time-consuming and may suffer from pathologist's subjectivity. Facing this problem, the development of automatic and precise diagnosis methods is challenging but also essential for the field. In this paper, we propose a new hybrid convolutional and recurrent deep neural network for breast cancer pathological image classification. Our method considers the short-term as well as the long-term spatial correlations between patches through RNN which is directly incorporated on top of a CNN feature extractor. Experimental results showed that our method obtained an average accuracy of 90.5% for 4-class classification task, which outperforms the state-of-the-art method. At the same time, we release a bigger dataset with 1568 breast cancer pathological images to the scientific community, which are now publicly available from http://ear.ict.ac.cn/?page id=1576. In particular, our dataset covers as many different subclasses spanning different age groups as possible, thus alleviating the problem of relatively low classification accuracy of benign.

Original language	English
Title of host publication	Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Editors	Harald Schmidt, David Griol, Haiying Wang, Jan Baumbach, Huiru Zheng, Zoraida Callejas, Xiaohua Hu, Julie Dickerson, Le Zhang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	957-962
Number of pages	6
ISBN (Electronic)	9781538654880
DOIs	https://doi.org/10.1109/BIBM.2018.8621429
Publication status	Published - 21 Jan 2019
Externally published	Yes
Event	2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 - Madrid, Spain Duration: 3 Dec 2018 → 6 Dec 2018

Publication series

Name	Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Conference

Conference	2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Country/Territory	Spain
City	Madrid
Period	3/12/18 → 6/12/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

CNN
RNN
breast cancer pathological image
dataset
deep neural network
image classification

Access to Document

10.1109/BIBM.2018.8621429

Cite this

Yan, R., Ren, F., Wang, Z., Wang, L., Ren, Y., Liu, Y., Rao, X., Zheng, C., & Zhang, F. (2019). A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification. In H. Schmidt, D. Griol, H. Wang, J. Baumbach, H. Zheng, Z. Callejas, X. Hu, J. Dickerson, & L. Zhang (Eds.), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 (pp. 957-962). Article 8621429 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2018.8621429

Yan, Rui ; Ren, Fei ; Wang, Zihao et al. / A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification. Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. editor / Harald Schmidt ; David Griol ; Haiying Wang ; Jan Baumbach ; Huiru Zheng ; Zoraida Callejas ; Xiaohua Hu ; Julie Dickerson ; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 957-962 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).

@inproceedings{43c0fae59ecc412e934b31d182247cfc,

title = "A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification",

abstract = "Hematoxylin and Eosin HE stained breast tissue samples from biopsies are observed under microscopy for the gold standard diagnosis of breast cancer. However, a substantial workload increases and the complexity of the pathological images make this task time-consuming and may suffer from pathologist's subjectivity. Facing this problem, the development of automatic and precise diagnosis methods is challenging but also essential for the field. In this paper, we propose a new hybrid convolutional and recurrent deep neural network for breast cancer pathological image classification. Our method considers the short-term as well as the long-term spatial correlations between patches through RNN which is directly incorporated on top of a CNN feature extractor. Experimental results showed that our method obtained an average accuracy of 90.5\% for 4-class classification task, which outperforms the state-of-the-art method. At the same time, we release a bigger dataset with 1568 breast cancer pathological images to the scientific community, which are now publicly available from http://ear.ict.ac.cn/?page id=1576. In particular, our dataset covers as many different subclasses spanning different age groups as possible, thus alleviating the problem of relatively low classification accuracy of benign.",

keywords = "CNN, RNN, breast cancer pathological image, dataset, deep neural network, image classification",

author = "Rui Yan and Fei Ren and Zihao Wang and Lihua Wang and Yubo Ren and Yudong Liu and Xiaosong Rao and Chunhou Zheng and Fa Zhang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 ; Conference date: 03-12-2018 Through 06-12-2018",

year = "2019",

month = jan,

day = "21",

doi = "10.1109/BIBM.2018.8621429",

language = "English",

series = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "957--962",

editor = "Harald Schmidt and David Griol and Haiying Wang and Jan Baumbach and Huiru Zheng and Zoraida Callejas and Xiaohua Hu and Julie Dickerson and Le Zhang",

booktitle = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",

address = "United States",

}

Yan, R, Ren, F, Wang, Z, Wang, L, Ren, Y, Liu, Y, Rao, X, Zheng, C & Zhang, F 2019, A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification. in H Schmidt, D Griol, H Wang, J Baumbach, H Zheng, Z Callejas, X Hu, J Dickerson & L Zhang (eds), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018., 8621429, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 957-962, 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Madrid, Spain, 3/12/18. https://doi.org/10.1109/BIBM.2018.8621429

A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification. / Yan, Rui; Ren, Fei; Wang, Zihao et al.
Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. ed. / Harald Schmidt; David Griol; Haiying Wang; Jan Baumbach; Huiru Zheng; Zoraida Callejas; Xiaohua Hu; Julie Dickerson; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. p. 957-962 8621429 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification

AU - Yan, Rui

AU - Ren, Fei

AU - Wang, Zihao

AU - Wang, Lihua

AU - Ren, Yubo

AU - Liu, Yudong

AU - Rao, Xiaosong

AU - Zheng, Chunhou

AU - Zhang, Fa

PY - 2019/1/21

Y1 - 2019/1/21

N2 - Hematoxylin and Eosin HE stained breast tissue samples from biopsies are observed under microscopy for the gold standard diagnosis of breast cancer. However, a substantial workload increases and the complexity of the pathological images make this task time-consuming and may suffer from pathologist's subjectivity. Facing this problem, the development of automatic and precise diagnosis methods is challenging but also essential for the field. In this paper, we propose a new hybrid convolutional and recurrent deep neural network for breast cancer pathological image classification. Our method considers the short-term as well as the long-term spatial correlations between patches through RNN which is directly incorporated on top of a CNN feature extractor. Experimental results showed that our method obtained an average accuracy of 90.5% for 4-class classification task, which outperforms the state-of-the-art method. At the same time, we release a bigger dataset with 1568 breast cancer pathological images to the scientific community, which are now publicly available from http://ear.ict.ac.cn/?page id=1576. In particular, our dataset covers as many different subclasses spanning different age groups as possible, thus alleviating the problem of relatively low classification accuracy of benign.

AB - Hematoxylin and Eosin HE stained breast tissue samples from biopsies are observed under microscopy for the gold standard diagnosis of breast cancer. However, a substantial workload increases and the complexity of the pathological images make this task time-consuming and may suffer from pathologist's subjectivity. Facing this problem, the development of automatic and precise diagnosis methods is challenging but also essential for the field. In this paper, we propose a new hybrid convolutional and recurrent deep neural network for breast cancer pathological image classification. Our method considers the short-term as well as the long-term spatial correlations between patches through RNN which is directly incorporated on top of a CNN feature extractor. Experimental results showed that our method obtained an average accuracy of 90.5% for 4-class classification task, which outperforms the state-of-the-art method. At the same time, we release a bigger dataset with 1568 breast cancer pathological images to the scientific community, which are now publicly available from http://ear.ict.ac.cn/?page id=1576. In particular, our dataset covers as many different subclasses spanning different age groups as possible, thus alleviating the problem of relatively low classification accuracy of benign.

KW - CNN

KW - RNN

KW - breast cancer pathological image

KW - dataset

KW - deep neural network

KW - image classification

UR - https://www.scopus.com/pages/publications/85062503949

U2 - 10.1109/BIBM.2018.8621429

DO - 10.1109/BIBM.2018.8621429

M3 - Conference contribution

AN - SCOPUS:85062503949

T3 - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

SP - 957

EP - 962

BT - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

A2 - Schmidt, Harald

A2 - Griol, David

A2 - Wang, Haiying

A2 - Baumbach, Jan

A2 - Zheng, Huiru

A2 - Callejas, Zoraida

A2 - Hu, Xiaohua

A2 - Dickerson, Julie

A2 - Zhang, Le

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Y2 - 3 December 2018 through 6 December 2018

ER -

Yan R, Ren F, Wang Z, Wang L, Ren Y, Liu Y et al. A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification. In Schmidt H, Griol D, Wang H, Baumbach J, Zheng H, Callejas Z, Hu X, Dickerson J, Zhang L, editors, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 957-962. 8621429. (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). doi: 10.1109/BIBM.2018.8621429

A Hybrid Convolutional and Recurrent Deep Neural Network for Breast Cancer Pathological Image Classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this