糖尿病性视网膜图像的深度神经网络分类方法

doi:10.11772/j.issn.1001-9081.2017.03.699

计算机应用 ›› 2017, Vol. 37 ›› Issue (3): 699-704.DOI: 10.11772/j.issn.1001-9081.2017.03.699

• 第二十五届全国多媒体技术学术会议(NCMT2016) • 上一篇下一篇

糖尿病性视网膜图像的深度神经网络分类方法

丁蓬莉, 李清勇, 张振, 李峰

北京交通大学轨道交通数据分析与挖掘北京市重点实验室, 北京 100044

收稿日期:2016-09-23 修回日期:2016-10-26 出版日期:2017-03-10 发布日期:2017-03-22
通讯作者: 李清勇
作者简介:丁蓬莉(1991-),女,山东潍坊人,硕士研究生,主要研究方向:机器学习、深度学习、模式识别、图像分类;李清勇(1979-),男,湖南娄底人,教授,博士,主要研究方向:机器视觉与模式识别、机器学习与数据挖掘;张振(1990-),男,河北唐山人,硕士研究生,主要研究方向:机器学习、深度学习、模式识别、图像分类;李峰(1992-),男,湖北黄冈人,硕士研究生,主要研究方向:机器学习、深度学习、模式识别、图像检测。
基金资助:
北京市自然科学基金资助项目（4142043）；中央高校基本科研业务费专项基金资助项目（2014JBZ003）。

Diabetic retinal image classification method based on deep neural network

DING Pengli, LI Qingyong, ZHANG Zhen, LI Feng

Beijing Key Lab of Transportation Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China

Received:2016-09-23 Revised:2016-10-26 Online:2017-03-10 Published:2017-03-22
Supported by:
This work is partially supported by Beijing Natural Science Foundation (4142043); the Fundamental Research Funds for the Central Universities (2014JBZ003).

摘要/Abstract

摘要： 针对传统的视网膜图像处理步骤复杂、泛化性差、缺少完整的自动识别系统等问题，提出了一套完整的基于深度神经网络的视网膜图像自动识别系统。首先，对图像进行去噪、归一化、数据扩增等预处理；然后，设计了紧凑的神经网络模型——CompactNet，CompactNet继承了AlexNet的浅层结构参数，深层网络参数则根据训练数据进行自适应调整；最后，针对不同的训练方法和不同的网络结构进行了性能测试。实验结果表明，CompactNet网络的微调方法要优于传统的网络训练方法，其分类指标可以达到0.87，与传统直接训练相比高出0.27；对于LeNet，AlexNet和CompactNet三种网络模型，CompactNet网络模型的分类准确率最高；并且通过实验证实了数据扩增等预处理方法的必要性。

关键词: 糖尿病性视网膜图像, 深度学习, 卷积神经网络, 图像分类, 微调

Abstract: Aiming at the problems of complex retinal image processing, poor generalization and lack of complete automatic recognition system, a complete retinal image automatic recognition system based on deep neural network was proposed. Firstly, the image was denoised, normalized, and data preprocessed. Then, a compact neural network model named CompactNet was designed. The structure parameters of CompactNet were inherited from AlexNet. The deep network parameters were adjusted adaptively based on the training data. Finally, the performance experiments were conducted on different training methods and various network structures. The experimental results demonstrate that the fine-tuning method of CompactNet is better than the traditional network training method, the classification index can reach 0.87, 0.27 higher than the traditional direct training. By comparing LeNet, AlexNet and CompactNet, CompactNet network model has the highest classification accuracy, and the necessity of preprocessing methods such as data amplification is confirmed by experiments.

Key words: diabetic retinal image, deep learning, convolutional neural network, image classification, fine-tune

中图分类号:

TP391.4

丁蓬莉, 李清勇, 张振, 李峰. 糖尿病性视网膜图像的深度神经网络分类方法[J]. 计算机应用, 2017, 37(3): 699-704.

DING Pengli, LI Qingyong, ZHANG Zhen, LI Feng. Diabetic retinal image classification method based on deep neural network[J]. Journal of Computer Applications, 2017, 37(3): 699-704.

参考文献

[1] L'HEVEDER R, NOLAN T. International diabetes federation[J]. Diabetes Research and Clinical Practice, 2013, 101(3):349-351.
[2] LEE S C, LEE E T, WANG Y, et al. Computer classification of nonproliferative diabetic retinopathy[J]. Archives of Ophthalmology, 2005, 123(6):759-764.
[3] LEE H, GROSSE R, RANGANATH R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]//Proceedings of the 26th Annual International Conference on Machine Learning. New York:ACM, 2009:609-616.
[4] 孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.(SUN Z J, XUE L, XU Y M, et al. Overview of deep learning[J]. Application Research of Computers, 2012, 29(8):2806-2810.)
[5] AREL I, ROSE D C, KARNOWSKI T P. Deep machine learning-a new frontier in artificial intelligence research[J]. IEEE Computational Intelligence Magazine, 2010, 5(4):13-18.
[6] 杨俊安,王一,刘辉,等.深度学习理论及其在语音识别领域的应用[J].通信对抗,2014(3):1-5.(YANG J A, WANG Y, LIU H, et al. Deep learning theory and its application in speech recognition[J]. Communication Countermeasures, 2014(3):1-5.)
[7] MOHAMED A, SAINATH T N, DAHL G, et al. Deep belief networks using discriminative features for phone recognition[C]//Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2011:5060-5063.
[8] SARIKAYA R, HINTON G E, DEORAS A. Application of deep belief networks for natural language understanding[J]. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2014, 22(4):778-784.
[9] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[10] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[EB/OL].[2016-03-02]. http://www.csd.uwo.ca/~olga/Courses/Fall2015/CS9840/Papers/imagenet.pdf.
[11] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:1-8.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2015-11-04]. http://www.robots.ox.ac.uk:5000/~vgg/publications/2015/Simonyan15/simonyan15.pdf.
[13] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[EB/OL].[2016-01-04]. https://www.researchgate.net/publication/286512696_Deep_Residual_Learning_for_Image_Recognition.
[14] HUBEL D H, WIESEL T N. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex[J]. Journal of Physiology, 1962, 160(1):106-154.
[15] LI S, KWOK J T, ZHU H, et al. Texture classification using the support vector machines[J]. Pattern Recognition, 2003, 36(12):2883-2893.

糖尿病性视网膜图像的深度神经网络分类方法

Diabetic retinal image classification method based on deep neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[4]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[5]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[6]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[7]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[8]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[9]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[10]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[11]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[12]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[13]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[14]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[15]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.