首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221021--1)

基于改进ResNeXt的乳腺癌组织病理学图像分类

Breast Cancer Histopathological Image Classification Based on Improved ResNeXt

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为实现对乳腺癌组织病理图像的准确自动分级,提出了一种改进的卷积神经网络,依次引入两种不同的卷积结构,以提高网络对病理图像的识别准确率。以深度残差网络(ResNeXt)为基础网络,用八度卷积(OctConv)替代传统卷积层,在特征提取阶段降低特征图中的冗余特征,提高了细节特征的提取效果;用异构卷积(HetConv)代替网络中的部分传统卷积层,以降低模型的训练参数。为了克服因数据样本较少出现的过拟合问题,采用一种基于图像分块思想的数据增强方法。实验结果表明,该网络在图像级别的四分类任务中准确率达到91.25%,表明所设计的网络模型具有较高的识别率和较好的实时性。

Abstract

In this paper, to achieve accurate automatic classification of breast cancer histopathological images, an improved convolutional neural network is proposed, and two different convolutional structures are introduced in order to improve the accuracy of histopathological image recognition by the network. Based on using deep residual network (ResNeXt) as basic network, octave convolution (OctConv) is used to replace the traditional convolutional layer to reduce the redundant features in the feature map during feature extraction stage and improve the effect of detailed feature extraction. Heterogeneous convolution (HetConv) is introduced to replace part of the traditional convolutional layers in the network, reducing model training parameters. To overcome the problem of over-fitting due to the small number of data samples, an effective data enhancement method based on the idea of image block is adopted. The experimental results demonstrate that the accuracy of the network on the four classification tasks of the network at the image level reaches 91.25%, indicating that the designed network model has a higher recognition rate and a better real-time performance.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.41

DOI:10.3788/LOP57.221021

所属栏目:图像处理

基金项目:国家自然科学基金、 内蒙古自治区科技计划、 内蒙古自治区自然科学基金、 内蒙古自治区高等学校科学研究项目、 内蒙古杰青培育项目、 包头市科技计划、 包头市青年创新人才项目、 教育部“春晖计划”合作科研项目;

收稿日期:2020-04-03

修改稿日期:2020-04-27

网络出版日期:2020-11-01

作者单位    点击查看

牛学猛:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010
吕晓琪:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010内蒙古工业大学信息工程学院, 内蒙古 呼和浩特 010051
谷宇:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010上海大学计算机工程与科学学院, 上海 200444
张宝华:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010
张明:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010大连海事大学信息科学技术学院, 辽宁 大连 116026
任国印:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010
李菁:内蒙古科技大学信息工程学院模式识别与智能图像处理重点实验室, 内蒙古 包头 014010

联系人作者:吕晓琪(lxiaoqi@imut.edu.cn)

备注:国家自然科学基金、 内蒙古自治区科技计划、 内蒙古自治区自然科学基金、 内蒙古自治区高等学校科学研究项目、 内蒙古杰青培育项目、 包头市科技计划、 包头市青年创新人才项目、 教育部“春晖计划”合作科研项目;

【1】Spanhol F A, Oliveira L S, Petitjean C, et al. A dataset for breast cancer histopathological image classification [J]. IEEE Transactions on Biomedical Engineering. 2016, 63(7): 1455-1462.Spanhol F A, Oliveira L S, Petitjean C, et al. A dataset for breast cancer histopathological image classification [J]. IEEE Transactions on Biomedical Engineering. 2016, 63(7): 1455-1462.

【2】Spanhol F A, Oliveira L S, Petitjean C, et al. Breast cancer histopathological image classification using convolutional neural networks . [C]//2016 International Joint Conference on Neural Networks (IJCNN), July 24-29, 2016, Vancouver, BC, Canada. New York: IEEE. 2016, 2560-2567.

【3】Araújo T, Aresta G, Castro E, et al. Classification of breast cancer histology images using convolutional neural networks [J]. PLOS One. 2017, 12(6): e0177544.Araújo T, Aresta G, Castro E, et al. Classification of breast cancer histology images using convolutional neural networks [J]. PLOS One. 2017, 12(6): e0177544.

【4】Golatkar A, Anand D, Sethi A. Classification of breast cancer histology using deep learning [2020-03-23].https://arxiv.[2020-03-23]. 0, org/abs/1802: 08080.

【5】Rakhlin A, Shvets A, Iglovikov V, et al. Deep convolutional neural networks for breast cancer histology image analysis [M]. //Rakhlin A, Shvets A, Iglovikov V, et al. Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science. Cham: Springer. 2018, 10882: 737-744.

【6】Koné I, Boulmane L. Hierarchical ResNeXt models for breast cancer histology image classification [M]. //Campilho A, Karray F, ter Haar Romeny B. et al. Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science. Cham: Springer. 2018, 10882: 796-803.

【7】Nazeri K, Aminpour A, Ebrahimi M. Two-stage convolutional neural network for breast cancer histology image classification [2020-03-21].https://arxiv.[2020-03-21]. 0, org/abs/1803: 04054.

【8】Wang Z H, You K Y, Xu J J, et al. Consensus design for continuous-time multi-agent systems with communication delay [J]. Journal of Systems Science and Complexity. 2014, 27(4): 701-711.

【9】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM. 2017, 60(6): 84-90.Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM. 2017, 60(6): 84-90.

【10】Gu Y, Lu X Q, Yang L D, et al. Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs [J]. Computers in Biology and Medicine. 2018, 103: 220-231.

【11】Meng T, Liu Y H, Zhang K Y. Algorithm for pathological image diagnosis based on boosting convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(8): 081001.
孟婷, 刘宇航, 张凯昱. 一种基于增强卷积神经网络的病理图像诊断算法 [J]. 激光与光电子学进展. 2019, 56(8): 081001.

【12】Li S M, Lei G Q, Fan R. Depth map super-resolution based on two-channel convolutional neural network [J]. Acta Optica Sinica. 2018, 38(10): 1010002.
李素梅, 雷国庆, 范如. 基于双通道卷积神经网络的深度图超分辨研究 [J]. 光学学报. 2018, 38(10): 1010002.

【13】Xie S N, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 5987-5995.

【14】Chen Y P, Fan H Q, Xu B, et al. Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution . [C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South). New York: IEEE. 2019, 3434-3443.

【15】Singh P, Verma V K, Rai P, et al. HetConv: heterogeneous kernel-based convolutions for deep CNNs . [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: IEEE. 2019, 4830-4839.

【16】Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift [2020-03-23].https://arxiv.[2020-03-23]. 0, org/abs/1502: 03167.

【17】Xu B, Wang N, Chen T, et al. Empirical evaluation of rectified activations in convolutional network [EB/OL]. 2020.Xu B, Wang N, Chen T, et al. Empirical evaluation of rectified activations in convolutional network [EB/OL]. 2020.

【18】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 770-778.

【19】Lin M, Chen Q, Yan S C, et al. Network in network [2020-03-25].https://arxiv.[2020-03-25]. 0, org/abs/1312: 4400.

【20】Srivastava N. Improving neural networks with dropout [J]. University of Toronto. 2013, 53(9): 1689-1699.

【21】Liu L Y, Jiang H M, He P C, et al. On the variance of the adaptive learning rate and beyond [EB/OL]. 2020.Liu L Y, Jiang H M, He P C, et al. On the variance of the adaptive learning rate and beyond [EB/OL]. 2020.

【22】Kingma D, Ba J. Adam: a method for stochastic optimization [EB/OL]. 2020.Kingma D, Ba J. Adam: a method for stochastic optimization [EB/OL]. 2020.

【23】Aresta G, Araújo T, Kwok S, et al. BACH: grand challenge on breast cancer histology images [J]. Medical Image Analysis. 2019, 56: 122-139.

【24】Gu Y, Lu X Q, Zhang B H, et al. Automatic lung nodule detection using multi-scale dot nodule-enhancement filter and weighted support vector machines in chest computed tomography [J]. PLOS One. 2019, 14(1): e0210551.

【25】Guo L L, Li Y N. Histopathological image classification algorithm based on product of experts [J]. Laser & Optoelectronics Progress. 2018, 55(2): 021008.
郭琳琳, 李岳楠. 基于专家乘积系统的组织病理图像分类算法 [J]. 激光与光电子学进展. 2018, 55(2): 021008.

【26】Khan S, Islam N, Jan Z, et al. A novel deep learning based framework for the detection and classification of breast cancer using transfer learning [J]. Pattern Recognition Letters. 2019, 125: 1-6.

【27】Gu Y, Lu X Q, Wu L, et al. A novel microcalcification enhancement method for digital mammogram images based on NSCT and CLAHE [J]. Optical Technique. 2018, 44(1): 6-12.
谷宇, 吕晓琪, 吴凉, 等. 基于NSCT和CLAHE的乳腺钼靶X线图像微钙化点增强方法 [J]. 光学技术. 2018, 44(1): 6-12.

【28】Gupta V, Bhavsar A. Breast cancer histopathological image classification: is magnification important? . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 769-776.

【29】Bardou D, Zhang K, Ahmad S M. Classification of breast cancer based on histology images using convolutional neural networks [J]. IEEE Access. 2018, 6: 24680-24693.

【30】Gu Y, Lü X Q, Zhao Y, et al. Research on computer-aided diagnosis of breast tumors based on PSO-SVM [J]. Computer Simulation. 2015, 32(5): 344-349.
谷宇, 吕晓琪, 赵瑛, 等. 基于PSO-SVM的乳腺肿瘤辅助诊断研究 [J]. 计算机仿真. 2015, 32(5): 344-349.

【31】He X Y, Han Z Y, Wei B Z. Breast cancer histopathological image auto-classification using deep learning [J]. Computer Engineering and Applications. 2018, 54(12): 121-125.
何雪英, 韩忠义, 魏本征. 基于深度学习的乳腺癌病理图像自动分类 [J]. 计算机工程与应用. 2018, 54(12): 121-125.

引用该论文

Niu Xuemeng,Lü Xiaoqi,Gu Yu,Zhang Baohua,Zhang Ming,Ren Guoyin,Li Jing. Breast Cancer Histopathological Image Classification Based on Improved ResNeXt[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221021

牛学猛,吕晓琪,谷宇,张宝华,张明,任国印,李菁. 基于改进ResNeXt的乳腺癌组织病理学图像分类[J]. 激光与光电子学进展, 2020, 57(22): 221021

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF