计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231000042-5.doi: 10.11896/jsjkx.231000042

• 图像处理&多媒体技术 • 上一篇    下一篇

基于图卷积网络的糖尿病视网膜病变分级模型

杨雨帆, 袁立明, 王珂, 李弘毅, 李奕璇, 姚雨佳, 王婧祎   

  1. 天津理工大学计算机科学与工程学院 天津 300384
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 袁立明(yuanliming@tjut.edu.cn)
  • 作者简介:(xwzjypgf@163.com)
  • 基金资助:
    天津理工大学大学生创新创业训练计划项目(202110060108);天津理工大学研究生教育教学研究与改革项目(YBXM2318)

Grading Model for Diabetic Retinopathy Based on Graph Convolutional Network

YANG Yufan, YUAN Liming, WANG Ke, LI Hongyi, LI Yixuan, YAO Yujia, WANG Jingyi   

  1. School of Computer Science and Engineering,Tianjin University of Technology,Tianjin 300384 ,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:YANG Yufan,born in 2002,undergra-duate.His main research interests include machine learning and deep lear-ning.
    YUAN Liming,born in 1982,Ph.D,associate professor,postgraduate supervisor.His main research interests include machine learning and medical image analysis.
  • Supported by:
    Program of Undergraduate Innovation and Entrepreneurship Training in Tianjin University of Technology(202110060108) and Program of Research and Reform on Graduate Education and Teaching in Tianjin University of Technology(YBXM2318).

PDF (PC)

168

摘要： 糖尿病视网膜病变是一种高风险的致盲性疾病,若能及早发现病变情况,则可对症治疗,减缓或阻止患者进一步的视力丧失。目前已经有一些利用深度学习进行糖尿病视网膜疾病检测的成功案例。然而,这些方法通常只考虑了图像中像素之间的空间关系,而没有考虑到图像深层特征之间的关系。为此,提出了一种基于图卷积网络的糖尿病视网膜病变分级模型,旨在帮助医生和研究人员在临床实践和科研工作中更好地进行糖尿病视网膜病变图像的分级和诊断。本模型主要通过图卷积网络去捕捉图像深层特征间所蕴含的重要的分级信息,获得具有更强语义信息的特征,并在此基础上构建一个双路分支网络。此外,为了更好地进行特征融合,采用自适应权重机制来进一步提高分级性能。实验结果表明,所提出的方法利用图卷积网络可以充分学习到图像深层特征间的关系,从而提高分级性能,其分类准确率在 APTOS2019 数据集上达到约 84.8％,在 Messidor-2 数据集上达到约 68％。

关键词: 糖尿病视网膜病变分级, 卷积神经网络, 图卷积网络, 双路分支网络, 自适应权重机制

Abstract: Diabetic retinopathy is a high-risk blinding disease.If it is detected early,it can be treated to slow or stop further vision loss in patients.There have been some successful cases of using deep learning to conduct diabetic retinal disease detection.Nevertheless,these methods usually only consider the spatial relationship between pixels in images and do not take into account the relationship between deeper features of the images.For this reason,a graph convolutional network based diabetic retinopathy gra-ding model is proposed with the aim of helping doctors and researchers to better grade and diagnose diabetic retinopathy images in clinical practice and scientific research.This model mainly uses the graph convolutional network to capture the important grading information embedded among deep features of an image,to obtain features with stronger semantic information,and to construct a two-way branching network based on it.In addition,for better feature fusion,an adaptive weighting mechanism is used to further improve the grading performance.Experimental results show that the proposed method can fully learn the relationship between the deep features of the image by using the graph convolutional network,so as to improve the classification performance,and its classification accuracy reaches about 84.8% on the APTOS2019 dataset and about 68% on the Messidor-2 dataset.

Key words: Diabetic retinopathy grading, Convolutional neural network, Graph convolutional network, Two-way branch network, Adaptive weighting mechanism

中图分类号: 

  • TP391
[1]Fundus Diseases Group,Chinese Academy of Ophthalmology.Guidelines for Diabetic Retinopathy Clinical Diagnosis and Treatment in my country[J].Chinese Journal of Ophthalmology,2014,50(11):851-865.
[2]FAN J,ZHANG R,LU M,et al.Application of deeplearningmethods in the diagnosis ofdiabetic retinopathy[J].Acta Automatica Sinica,2021,47(5):20.
[3]ACHARYA U R,NG E,TAN J H,et al.An Integrated Index for the Identification of Diabetic Retinopathy Stages using Texture Parameters[J].Journal of Medical Systems,2012(3):36.
[4]WONG T Y,SUN J,KAWASAKI R,et al.Guidelines on Diabetic Eye Care[J].Ophthalmology,2018(10):125.
[5]LING Y,XI S.Correlation between diabetic retinopathy and dry eye[J].International Journal of Ophthalmology,2018,18(4):4.
[6]CUN L,JACKEL L D,BOSER B,et al.Handwritten Digit Recognition:Applications of Neural Network Chips and Automatic Learning[J].IEEE Communications Magazine,1989,27(11):41-46.
[7]SHI J,WANG R,ZHENG Y,et al.Cervical cell classificationwith graph convolutional network[J].Computer Methods and Programs in Biomedicine,2021,198:105807.
[8]KIPF T N,WELLING M.Semi-Supervised Classification withGraph Convolutional Networks[J].arXiv:609.02907,2017.
[9]SAJID S,HUSSAIN S,SARWAR A.Brain Tumor Detectionand Segmentation in MR Images Using Deep Learning[J].Arabian Journal for Science and Engineering,2019,44(11):9249-9261.
[10]WONG J A H A.Algorithm AS 136:A K-Means Clustering Algorithm[J].Journal of the Royal Statistical Society,1979,28(1):100-108.
[11]WANG S H,GOVINDARAJ V V,ÓRRIZ J M,et al.Covid-19 Classification by FGCNet with Deep Feature Fusion from Graph Convolutional Network and Convolutional Neural Network[J].Information Fusion,2020,67:208-229.
[12]Asia Pacific Tele-Ophthalmology Society.APTOS 2019 blindness detection [EB/OL].https://kaggle.com/competitions/aptos2019-blindness-detection.
[13]DECENCIÉRE E,ZHANG X,CAZUGUEL G,et al.Feedback on A Publicly Distributed Image Database:the Messidor Database[J].Image Analysis & Stereology,2014,33(3):231-234.
[14]HUANG G,LIU Z,LAURENS V,et al.Densely ConnectedConvolutional Networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017:2261-2269.
[15]HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[16]KELLER J M,GRAY M R,GIVENS J A.A fuzzy K-nearestneighbor algorithm[J].IEEE Transactions on Systems Man & Cybernetics,1985,SMC-15(4):580-585.
[17]DE BOER P T,KROESE D P,MANNOR S,et al.A tutorial on the cross-entropy method[J].Annals of Operations Research,2005,134(1):19-67.
[18]RAKHLIN A.Diabetic Retinopathy Detection through Integration of Deep Learning Classification Framework[J].bioRxiv.2017,225508.
[19]LI X,HU X,YU L,et al.CANet:Cross-Disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading[J].IEEE Transactions on Medical Imaging,2020,39(5):1483-1493.
[20]LIU S T,GONG L J,MA K,et al.GREEN:A Graph Residual Re-Ranking Network for Grading Diabetic Retinopathy[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.Lima,Peru,2020:585-594.
[21]POWERS D.Evaluation:From Precision,Recall and F-Measure to ROC,Informedness,Markedness and Correlation[J].Journal of Machine Learning Technologies,2011,2(1):37-63.
[22]HUANG G,LIU Z,VAN DER MAATEN L,et al.Denselyconnected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:4700-4708.
[23]TAN M,LE Q V.EfficientNet:Rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning.PMLR,2019:6105-6114.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发