Detection of Diabetic Retinopathy from Retinal Images Using DenseNet Models
作者机构:Department of ECEK S R Institute for Engineering and TechnologyTiruchengode637215India Department of Computer Science and EngineeringSRM Institute of Science and TechnologyChennai603203India Department of Electronics and Communication and EngineeringSRM Institute of Science and TechnologyChennai603203India
出 版 物:《Computer Systems Science & Engineering》 (计算机系统科学与工程(英文))
年 卷 期:2023年第45卷第4期
页 面:279-292页
核心收录:
学科分类:0710[理学-生物学] 1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 0837[工学-安全科学与工程] 100201[医学-内科学(含:心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 10[医学]
基 金:Department of CSE SRM Institute of Science and Technology, SRMIST
主 题:Convolutional Neural Networks vision loss pathogenic blood vessels DenseNet AlexNet ResNet
摘 要:A prevalent diabetic complication is Diabetic Retinopathy(DR),which can damage the retina’s veins,leading to a severe loss of *** treated in the early stage,it can help to prevent vision *** since its diagnosis takes time and there is a shortage of ophthalmologists,patients suffer vision loss even before ***,early detection of DR is the necessity of the *** primary purpose of the work is to apply the data fusion/feature fusion technique,which combines more than one relevant feature to predict diabetic retinopathy at an early stage with greater *** procedures for diabetic retinopathy analysis are fundamental in taking care of these *** profound learning for parallel characterization has accomplished high approval exactness’s,multi-stage order results are less noteworthy,especially during beginning phase *** Connected Convolutional Networks are suggested to detect of Diabetic Retinopathy on retinal *** presented model is trained on a Diabetic Retinopathy Dataset having 3,662 images given by *** results suggest that the training accuracy of 93.51%0.98 precision,0.98 recall and 0.98 F1-score has been achieved through the best one out of the three models in the proposed *** same model is tested on 550 images of the Kaggle 2015 dataset where the proposed model was able to detect No DR images with 96%accuracy,Mild DR images with 90%accuracy,Moderate DR images with 89%accuracy,Severe DR images with 87%accuracy and Proliferative DR images with 93%accuracy.