基于注意力机制的糖尿病视网膜病变分类算法

doi:10.11896/jsjkx.211000213

计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211000213-5.doi: 10.11896/jsjkx.211000213

• 图像处理&多媒体技术 • 上一篇下一篇

基于注意力机制的糖尿病视网膜病变分类算法

孙福权¹, 邹彭^1,2, 崔志清^1,2, 张琨¹

1 东北大学秦皇岛分校数学与统计学院河北秦皇岛 066000
2 东北大学信息科学与工程学院沈阳 110000

出版日期:2022-11-10 发布日期:2022-11-21
通讯作者: 邹彭(zp17853266007@163.com)
作者简介:(zp17853266007@163.com)
基金资助:
国家重点研发计划(2018YFB1402800);河北省高教研究与实践项目(2018GJJG422)

Classification Algorithm of Diabetic Retinopathy Based on Attention Mechanism

SUN Fu-quan¹, ZOU Peng^1,2, CUI Zhi-qing^1,2, ZHANG Kun¹

1 School of Mathematics and Statistics,Northeastern University at Qinhuangdao,Qinhuangdao,Hebei 066000,China
2 School of Information Science and Engineering,Northeastern University,Shenyang 110000,China

Online:2022-11-10 Published:2022-11-21
About author:SUN Fu-quan,born in 1964,Ph.D,postdoctoral fellow,professor.His main research interests include medical image processing and big data analysis.
ZOU Peng,born in 1998,postgraduate.His main research interests include image processing and computer vision.
Supported by:
National Key R & D Program of China(2018YFB1402800) and Hebei Higher Education Research and Practice Project(2018GJJG422).

摘要/Abstract

摘要： 糖尿病视网膜病变是糖尿病的重要并发症之一,是工作人群失明的主要原因。视网膜图像类间差距小,易混淆,由于医疗资源不足和缺乏有经验的眼科医生,难以进行大规模的视网膜图像筛查。为此,提出了一种基于注意力机制的糖尿病视网膜病变分类算法,实现对视网膜图像病变程度的精确分类。对数据集进行数据增强和图像增强等预处理操作,利用EfficientNetV2作为主干分类网络,在网络中加入注意力机制对视网膜图像进行细粒度分类,同时采用迁移学习策略对网络进行训练。所提算法的分类准确率和二次加权Kappa值分别为97.8%和0.843,能够有效地对视网膜图像进行病变程度分类,与其他模型相比具有优越性,对于糖尿病视网膜病变的诊断和治疗具有重要意义。

关键词: 深度学习, 糖尿病视网膜病变分类, 注意力机制, 数据预处理, 迁移学习

Abstract: Diabetic retinopathy is one of the important complications of diabetes and the main cause of blindness in the working population.The gap between retinal images is small and easy to be confused.Due to insufficient medical resources and lack of experienced ophthalmologists,it is difficult to carry out large-scale retinal image screening.Therefore,a classification algorithm for diabetic retinopathy based on attention mechanism is proposed to achieve accurate classification of the degree of retinal image lesions.The preprocessing operations such as data enhancement and image enhancement are carried out on data set.Using EfficientNetV2 as the backbone classification network,the attention mechanism is added to the network for fine-grained classification of retinal images,and the transfer learning strategy is used to train the network.The classification accuracy and the second weighted Kappa value of the proposed model are 97.8% and 0.843 respectively,which can effectively classify the disease degree of retinal images.Compared with other models,it has advantages and is of great significance for the diagnosis and treatment of diabetic retinopathy.

Key words: Deep learning, Classification of diabetic retinopathy, Attention mechanism, Data preprocessing, Transfer learning

中图分类号:

TP393

孙福权, 邹彭, 崔志清, 张琨. 基于注意力机制的糖尿病视网膜病变分类算法[J]. 计算机科学, 2022, 49(11A): 211000213-5. https://doi.org/10.11896/jsjkx.211000213

SUN Fu-quan, ZOU Peng, CUI Zhi-qing, ZHANG Kun. Classification Algorithm of Diabetic Retinopathy Based on Attention Mechanism[J]. Computer Science, 2022, 49(11A): 211000213-5. https://doi.org/10.11896/jsjkx.211000213

参考文献

[1]WANG W,AMY L.Diabetic Retinopathy:Pathophysiology andTreatments[J].International Journal of Molecular Ences,2018,19(6):1816.
[2]XU Y,WANG L,HE J,et al.Prevalence and control of diabetes in Chinese adults[J].Journal of American Medical Association,2013,310(9):948-959.
[3]SALEH M,ESWARAN C.An Automated Decision-SupportSystem for Nonproliferative Diabetic Retinopathy Disease Based on Mas and Has Detection[J].Computer Methods and Programs in Biomedicine,2012,108(1):186-196.
[4]WANG G L.The review and consideration on grading in diabetic retinopathy[J].Ophthalmol,2005(4):218-220.
[5]LU G H.The blood glucose threshold of diabetic retinopathy:impact on the diagnostic criteria of diabetes[J].Journal of Practical Diabetology,2011,7(2):55-59.
[6]DU J H,ZHANG L,YAO Y,et al.Preliminary study on thegrading diagnosis and treatment measures of diabetic retinopathy[J].Diabetes New World,2018,21(7):190-191.
[7]RAJENDRA A U,CHUA C K,NG E Y K,et al.Application of Higher Order Spectra for the Identification of Diabetes Retino-pathy Stages[J].Journal of Medical Systems,2008,32(6):481-488.
[8]ADARSH P,JEYAKUMARI D.Multiclass SVM-Based Auto-mated Diagnosis of Diabetic Retinopathy[C]//2013 Interna-tional Conference on Communications and Signal Processing.IEEE,2013:206-210.
[9]PRATT H,COENEN F,BROADBENT D M,et al.Convolu-tional Neural Networks for Diabetic Retinopathy[J].Procedia Computer Science,2016,90(3):200-205.
[10]SIMONYAN K,ZISSERMAN A.Very deep convolutional net-works for large-scale image recognition[J].arXiv:1409.1556,2014.
[11]DING P L,LI Q Y,ZHANG Z,et al.Deep neural network classification method for diabetic retinal images[J].Computer Applications,2017,37(3):699-704.
[12]ARKADIUSZ K,BARTLOMIEJ J,MICHALG.Deep CNNBased Decision Support System for Detection and Assessing the Stage of Diabetic Retinopathy[C]//2018 International Interdisciplinary Ph.D Workshop(IIPh.DW).IEEE,2018:111-116.
[13]WANG Z,YIN Y,SHI J,et al.Zoom-in-net:Deep mining lesions for diabetic retinopathy detection[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2017:267-275.
[14]ZHAO Z,ZHANG K,HAO X,et al.Bira-net:Bilinear attention net for diabetic retinopathy grading[C]//2019 IEEE International Conference on Image Processing(ICIP).IEEE,2019:1385-1389.
[15]TAN M,LE Q V.Efficientnetv2:Smaller models and fastertraining[J].arXiv:2014.00298,2021.
[16]TAN M,LE Q V.EfficientNet:Rethinking Model Scaling for Convolutional Neural Networks[C]//International Conference on Machine Learning.PMLR,2019,6105-6114.
[17]HAO S,LEE D H,ZHAO D.Sequence to sequence learningwith attention mechanism for short-term passenger flow prediction in large-scale metro system[J].Transportation Research Part C:Emerging Technologies,2019,107(10):287-300.
[18]MIKOLAJCZYK A,GROCHOWSKIM.Data augmentation for improving deep learning in image classification problem[C]//2018 International Interdisciplinary Ph.D Workshop(IIPh.DW).IEEE,2018:117-122.
[19]WANG Y,WANG G A,FAN W G,et al.A deep learning based pipeline for image of diabetic retinopathy[C]//International Conference on Smart Health.Cham:Springer,2018:240-248.
[20]DOSHI D,SHENOY A,SIDHPURA D,et al.Diabetic retinopathy detection using deep convolutional neural networks[C]//2016 International Conference on Computing,Analytics and Security Trends(CAST).IEEE,2016:261-266.
[21]ZHOU K,GU Z,LIU W,et al.Multi-cell multi-task convolutional neural networks for diabetic retinopathy grading[C]//2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC).IEEE,2018:2724-2727.

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[5]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[6]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[7]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[8]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[9]	方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法 Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning 计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[10]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[11]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[12]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[13]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[14]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[15]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于注意力机制的糖尿病视网膜病变分类算法

Classification Algorithm of Diabetic Retinopathy Based on Attention Mechanism

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0