Breast cancer pathological image classification based on a convolutional neural network

被引：0

作者：

Yu L. ^{[1
]}

Xia Y. ^{[1
]}

Yan Y. ^{[1
]}

Wang P. ^{[1
]}

Cao W. ^{[1
]}

机构：

[1] College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin

来源：

Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University | 2021年 / 42卷 / 04期

关键词：

Breast cancer; Convolutional neural network; Deep learning; Fusion algorithm; Image blocking; Image classification; Pathological image; Transfer learning;

D O I：

10.11990/jheu.201909052

中图分类号：

学科分类号：

摘要：

To solve the problems of low accuracy and time-consuming and laborious classification of breast pathological images, this paper proposes a method of using a convolutional neural network (CNN) to classify breast pathological images. This method is used to divide pathological images quickly and automatically into the benign and malignant categories. First, the CNN model based on the Inceptionv3 architecture and the transfer learning algorithm are used for pathological image feature extraction; the fully connected layer neural network and the SoftMax function are used for image classification. At the same time, the idea of image partitioning is proposed for high-resolution images. To obtain the final classification result of the image, the classification probability of each block is integrated through three algorithms: summation, product, and maximum. Experiments were carried out on the BreaKHis public dataset, and the accuracy reached 95.0%, 95.1%, 94.1%, and 92.3% respectively on the four magnification coefficients. It shows that the method effectively improves the classification accuracy of breast cancer pathological images. Copyright ©2021 Journal of Harbin Engineering University.

引用

页码：567 / 573

页数：6

共 18 条

[1] BRAY F, FERLAY J, SOERJOMATARAM I, Et al., Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA: a cancer journal for clinicians, 68, 6, pp. 394-424, (2018)
[2] YANG Feng, LI Jinfeng, WHO classification of tumors of the breast, Chinese journal of surgery, 52, 1, pp. 1-3, (2014)
[3] ELMORE J G, LONGTON G M, CARNEY P A, Et al., Diagnostic concordance among pathologists interpreting breast biopsy specimens[J], JAMA, 313, 11, pp. 1122-1132, (2015)
[4] BELSARE A D, MUSHRIF M M, PANGARKAR M A, Et al., Classification of breast cancer histopathology images using texture feature analysis, Proceedings of 2015 IEEE Region 10 Conference, (2015)
[5] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, Et al., A dataset for breast cancer histopathological image classification, IEEE transactions on biomedical engineering, 63, 7, pp. 1455-1462, (2016)
[6] HAMILTON N A, PANTELIC R S, HANSON K, Et al., Fast automated cell phenotype image classification, BMC bioinformatics, 8, 1, (2007)
[7] ZHANG Yanbo, YU Hengyong, Convolutional neural network based metal artifact reduction in X-ray computed tomography, IEEE transactions on medical imaging, 37, 6, pp. 1370-1381, (2018)
[8] ARAUJO T, ARESTA G, CASTRO E, Et al., Classification of breast cancer histology images using Convolutional Neural Networks, PLoS one, 12, 6, (2017)
[9] HE Xueying, HAN Zhongyi, WEI Benzheng, Breast cancer histopathological image auto-classification using deep learning, Computer engineering and applications, 54, 12, pp. 121-125, (2018)
[10] SPANHOL F A, OLIVEIRA L S, PETITJEAN C, Et al., Breast cancer histopathological image classification using convolutional neural networks, Proceedings of 2016 International Joint Conference on Neural Networks, (2016)

← 1 2 →