Classification of Fundus Images Using Convolutional Neural Networks

R. Sabitha, G. Ramani
{"title":"Classification of Fundus Images Using Convolutional Neural Networks","authors":"R. Sabitha, G. Ramani","doi":"10.1166/jmihi.2022.3947","DOIUrl":null,"url":null,"abstract":"Diabetes causes damage to the retinal blood vessel networks, resulting in Diabetic Retinopathy (DR). This is a serious vision-threatening condition for most diabetics. Color fundus photographs are utilized to diagnose DR, which necessitates the employment of qualified clinicians to\n detect the presence of lesions. It is difficult to identify DR in an automated method. Feature extraction is quite important in terms of automated sickness detection. Convolutional Neural Network (CNN) exceeds previous handcrafted feature-based image classification algorithms in terms of picture\n classification efficiency in the current environment. In order to improve classification accuracy, this work presents the CNN structure for extracting attributes from retinal fundus images. The output properties of CNN are given as input to different machine learning classifiers in this recommended\n strategy. This approach is evaluating using pictures from the EYEPACS datasets using Decision stump, J48 and Random Forest classifiers. To determine the effectiveness of a classifier, its accuracy, false positive rate (FPR), True positive Rate (TPR), precision, recall, F-measure, and Kappa-score\n are illustrated. The recommended feature extraction strategy paired with the Random forest classifier outperforms all other classifiers on the EYEPACS datasets, with average accuracy and Kappa-score (k-score) of 99% and 0.98 respectively.","PeriodicalId":49032,"journal":{"name":"Journal of Medical Imaging and Health Informatics","volume":"7 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Medical Imaging and Health Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1166/jmihi.2022.3947","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Diabetes causes damage to the retinal blood vessel networks, resulting in Diabetic Retinopathy (DR). This is a serious vision-threatening condition for most diabetics. Color fundus photographs are utilized to diagnose DR, which necessitates the employment of qualified clinicians to detect the presence of lesions. It is difficult to identify DR in an automated method. Feature extraction is quite important in terms of automated sickness detection. Convolutional Neural Network (CNN) exceeds previous handcrafted feature-based image classification algorithms in terms of picture classification efficiency in the current environment. In order to improve classification accuracy, this work presents the CNN structure for extracting attributes from retinal fundus images. The output properties of CNN are given as input to different machine learning classifiers in this recommended strategy. This approach is evaluating using pictures from the EYEPACS datasets using Decision stump, J48 and Random Forest classifiers. To determine the effectiveness of a classifier, its accuracy, false positive rate (FPR), True positive Rate (TPR), precision, recall, F-measure, and Kappa-score are illustrated. The recommended feature extraction strategy paired with the Random forest classifier outperforms all other classifiers on the EYEPACS datasets, with average accuracy and Kappa-score (k-score) of 99% and 0.98 respectively.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于卷积神经网络的眼底图像分类
糖尿病引起视网膜血管网络损伤,导致糖尿病性视网膜病变(DR)。对大多数糖尿病患者来说,这是一种严重的视力威胁。彩色眼底照片用于诊断DR,这就需要聘请合格的临床医生来检测病变的存在。用自动化方法识别DR是困难的。特征提取在自动疾病检测中非常重要。卷积神经网络(CNN)在当前环境下的图像分类效率超过了以往手工制作的基于特征的图像分类算法。为了提高分类精度,本文提出了一种用于提取视网膜眼底图像属性的CNN结构。在这个推荐的策略中,CNN的输出属性作为输入给不同的机器学习分类器。该方法使用Decision stump、J48和Random Forest分类器对来自EYEPACS数据集的图片进行评估。为了确定分类器的有效性,说明了其准确性,假阳性率(FPR),真阳性率(TPR),精度,召回率,f测量和kappa评分。推荐的特征提取策略与随机森林分类器配对,在EYEPACS数据集上优于所有其他分类器,平均准确率和k-score (k-score)分别为99%和0.98。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Journal of Medical Imaging and Health Informatics
Journal of Medical Imaging and Health Informatics MATHEMATICAL & COMPUTATIONAL BIOLOGY-RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
自引率
0.00%
发文量
0
审稿时长
6-12 weeks
期刊介绍: Journal of Medical Imaging and Health Informatics (JMIHI) is a medium to disseminate novel experimental and theoretical research results in the field of biomedicine, biology, clinical, rehabilitation engineering, medical image processing, bio-computing, D2H2, and other health related areas. As an example, the Distributed Diagnosis and Home Healthcare (D2H2) aims to improve the quality of patient care and patient wellness by transforming the delivery of healthcare from a central, hospital-based system to one that is more distributed and home-based. Different medical imaging modalities used for extraction of information from MRI, CT, ultrasound, X-ray, thermal, molecular and fusion of its techniques is the focus of this journal.
期刊最新文献
Medical Imaging and Health Informatics Liver Cancer Detection and Classification Using Raspberry Pi A Rapid Dual Feature Tracking Method for Medical Equipments Assembly and Disassembly in Markerless Augmented Reality Deep Learning-Based Electrocardiogram Signal Analysis for Abnormalities Detection Using Hybrid Cascade Feed Forward Backpropagation with Ant Colony Optimization Technique Volume Subtraction Method Using Dual Reconstruction and Additive Technique for Pulmonary Artery/Vein 3DCT Angiography
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1