基于弱监督的改进型GoogLeNet在DR检测中的应用

doi:10.11772/j.issn.1001-9081.2019010225

计算机应用 ›› 2019, Vol. 39 ›› Issue (8): 2484-2488.DOI: 10.11772/j.issn.1001-9081.2019010225

• 应用前沿、交叉与综合 • 上一篇

基于弱监督的改进型GoogLeNet在DR检测中的应用

丁英姿¹, 丁香乾¹, 郭保琪²

1. 中国海洋大学信息科学与工程学院, 山东青岛 266100;
2. 青岛海大新星计算机工程中心大数据联合实验室, 山东青岛 266071

收稿日期:2019-01-30 修回日期:2019-03-12 出版日期:2019-08-10 发布日期:2019-04-15
通讯作者: 郭保琪
作者简介:丁英姿(1983-),男,山东荣成人,博士研究生,主要研究方向:深度学习、计算机视觉;丁香乾(1962-),男,山东荣成人,教授,博士生导师,硕士,主要研究方向:计算智能、软件工程、现代服务业、制造业信息化;郭保琪(1982-),男,山东德州人,硕士,主要研究方向:深度学习、人工智能、智慧医疗。
基金资助:
国家重点研发计划项目（2016YFB1001103）。

Application of improved GoogLeNet based on weak supervision in DR detection

DING Yingzi¹, DING Xiangqian¹, GUO Baoqi²

1. College of Information Science and Engineering, Ocean University of China, Qingdao Shandong 266100, China;
2. Big Data Joint Laboratory, Qingdao New Star Computer Engineering Center, Qingdao Shandong 266071, China

Received:2019-01-30 Revised:2019-03-12 Online:2019-08-10 Published:2019-04-15
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2016YFB1001103).

摘要/Abstract

摘要： 针对糖尿病视网膜病变分级检测中标定样本少、多目标检测的问题，提出了一种基于改进型GoogLeNet的弱监督目标检测网络。首先，对GoogLeNet网络进行改进，去掉最后一个全连接层并保留检测目标的位置信息，添加全局最大池化层，以sigmoid交叉熵作为训练的目标函数以获得带有多种特征位置信息的特征图；然后，基于弱监督方法仅使用类别标签对网络进行训练；其次，设计一种连通区域算法来计算特征连通区域边界坐标集合；最后在待测图片中使用边界框定位病灶。实验结果表明，在小样本条件下，改进模型准确率达到了94.5%，与SSD算法相比，准确率提高了10%。改进模型实现了小样本条件下端到端的病变识别，同时该模型的高准确率保证了模型在眼底筛查中具有应用价值。

关键词: 糖尿病视网膜病变, 弱监督, 卷积神经网络, 目标检测网络, 全局最大池化

Abstract: To handle the issues of small sample size and multi-target detection in the hierarchical detection of diabetic retinopathy, a weakly supervised target detection network based on improved GoogLeNet was proposed. Firstly, the GoogLeNet network was improved, the last fully-connected layer of the network was removed and the position information of the detection target was retained. A global max pooling layer was added, and the sigmoid cross entropy was used as the objective function of training to obtain the feature map with multiple feature position information. Secondly, based on the weak supervision method, only the category label was used to train the network. Thirdly, a connected region algorithm was designed to calculate the boundary coordinate set of feature connected regions. Finally, the boundary box was used to locate the lesion in the image to be tested. Experimental results show that under the small sample condition, the accuracy of the improved model reaches 94%, which is improved by 10% compared with SSD (Single Shot mltibox Detector) algorithm. The improved model realizes end-to-end lesion recognition under small sample condition, and the high accuracy of the model ensures its application value in fundus screening.

Key words: Diabetic Retinopathy (DR), weak supervision, Convolutional Neural Networks (CNN), target detection network, Global Max Pooling (GMP)

中图分类号:

TP391.41

丁英姿, 丁香乾, 郭保琪. 基于弱监督的改进型GoogLeNet在DR检测中的应用[J]. 计算机应用, 2019, 39(8): 2484-2488.

DING Yingzi, DING Xiangqian, GUO Baoqi. Application of improved GoogLeNet based on weak supervision in DR detection[J]. Journal of Computer Applications, 2019, 39(8): 2484-2488.

参考文献

[1] PRIYA R,ARUNA P. Review of automated diagnosis of diabetic retinopathy using the support vector machine[J]. International Journal of Applied Engineering Research, 2011, 1(4):844-862.
[2] PRIYA R, ARUNA P. SVM and neural network based diagnosis of diabetic retinopathy[J]. International Journal of Computer Applications,2012,41(1):6-12.
[3] 丁蓬莉.基于深度学习的糖尿病性视网膜分析算法研究[D].北京:北京交通大学,2017:22-23. (DING P L. Research of diabetic retinal image analysis algorithms based on deep learning[D]. Beijing:Beijing Jiaotong University, 2017:22-23.)
[4] 蔡石林.基于CNN的糖尿病视网膜病变识别算法研究与实现[D].长沙:湖南大学,2018:22-25. (CAI S L. Research and implementation on diabetic retinopathy recognition algorithm based on CNN[D]. Changsha:Hunan University, 2018:22-25.)
[5] 马文俊.基于机器学习的糖尿病视网膜病变分级研究[D].哈尔滨:哈尔滨工程大学,2017:28-31. (MA W J. Study on classification of diabetic retinopathy based on machine learning[D]. Harbin:Harbin Engineering University, 2017:28-31.)
[6] 张德彪.基于深度学习的糖尿病视网膜病变分类和病变检测方法的研究[D].哈尔滨:哈尔滨工业大学,2017:25-29. (ZHANG D B. Research on diabetic retinopathy classification and lesion detection based on deep learning[D]. Harbin:Harbin Institute of Technology, 2017:25-29.)
[7] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2015:1440-1448.
[8] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of the 2015 International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2015:91-99.
[9] DAI J, LI Y, HE K, et al. R-FCN:object detection via region-based fully convolutional networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. North Miami Beach, FL:Curran Associates Inc., 2016:379-387.
[10] OQUAB M, BOTTOUB L, LAPTEV I, et al. Learning and transferring mid-level image representations using convolutional neural networks[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:1717-1724.
[11] OQUAB M, BOTTOUB L, LAPTEV I, et al. Is object localization for free?-weakly-supervised learning with convolutional neural networks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:685-694.
[12] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Object detectors emerge in deep scene CNNs[J]. arXiv E-print, 2015:arXiv:1412.6856.
[13] ZHOU B, KHOSLA A, LAPEDRIZA, OLIVA A, et al. Learning deep features for discriminative localization[C]//Proceedings of the 2016 the IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC:IEEE Computer Society, 2016:2921-2929.
[14] 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, 2015:1-9.
[15] LIN M, CHEN Q, YAN S. Network in network[J]. arXiv E-print, 2014:arXiv:1312.4400.
[16] SZEGEDY C, VANHOUCKE V, LOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:2818-2826.

基于弱监督的改进型GoogLeNet在DR检测中的应用

Application of improved GoogLeNet based on weak supervision in DR detection

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]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[9]	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.
[10]	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.
[11]	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.
[12]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[13]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[14]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[15]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.