A Hybrid Convolutional Neural Network Model for Automatic Diabetic Retinopathy Classification From Fundus Images

IF 3.7 3区医学 Q2 ENGINEERING, BIOMEDICAL

IEEE Journal of Translational Engineering in Health and Medicine-Jtehm Pub Date : 2023-06-01 DOI:10.1109/JTEHM.2023.3282104

Ghulam Ali;Aqsa Dastgir;Muhammad Waseem Iqbal;Muhammad Anwar;Muhammad Faheem

{"title":"A Hybrid Convolutional Neural Network Model for Automatic Diabetic Retinopathy Classification From Fundus Images","authors":"Ghulam Ali;Aqsa Dastgir;Muhammad Waseem Iqbal;Muhammad Anwar;Muhammad Faheem","doi":"10.1109/JTEHM.2023.3282104","DOIUrl":null,"url":null,"abstract":"<italic>Objective:</i>\n Diabetic Retinopathy (DR) is a retinal disease that can cause damage to blood vessels in the eye, that is the major cause of impaired vision or blindness, if not treated early. Manual detection of diabetic retinopathy is time-consuming and prone to human error due to the complex structure of the eye. \n<italic>Methods & Results:</i>\n various automatic techniques have been proposed to detect diabetic retinopathy from fundus images. However, these techniques are limited in their ability to capture the complex features underlying diabetic retinopathy, particularly in the early stages. In this study, we propose a novel approach to detect diabetic retinopathy using a convolutional neural network (CNN) model. The proposed model extracts features using two different deep learning (DL) models, Resnet50 and Inceptionv3, and concatenates them before feeding them into the CNN for classification. The proposed model is evaluated on a publicly available dataset of fundus images. The experimental results demonstrate that the proposed CNN model achieves higher accuracy, sensitivity, specificity, precision, and f1 score compared to state-of-the-art methods, with respective scores of 96.85%, 99.28%, 98.92%, 96.46%, and 98.65%.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"341-350"},"PeriodicalIF":3.7000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/6221039/9961067/10142165.pdf","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10142165/","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 4

Abstract

Objective: Diabetic Retinopathy (DR) is a retinal disease that can cause damage to blood vessels in the eye, that is the major cause of impaired vision or blindness, if not treated early. Manual detection of diabetic retinopathy is time-consuming and prone to human error due to the complex structure of the eye. Methods & Results: various automatic techniques have been proposed to detect diabetic retinopathy from fundus images. However, these techniques are limited in their ability to capture the complex features underlying diabetic retinopathy, particularly in the early stages. In this study, we propose a novel approach to detect diabetic retinopathy using a convolutional neural network (CNN) model. The proposed model extracts features using two different deep learning (DL) models, Resnet50 and Inceptionv3, and concatenates them before feeding them into the CNN for classification. The proposed model is evaluated on a publicly available dataset of fundus images. The experimental results demonstrate that the proposed CNN model achieves higher accuracy, sensitivity, specificity, precision, and f1 score compared to state-of-the-art methods, with respective scores of 96.85%, 99.28%, 98.92%, 96.46%, and 98.65%.

查看原文本刊更多论文

基于眼底图像的糖尿病视网膜病变自动分类的混合卷积神经网络模型

目的：糖尿病视网膜病变（DR）是一种视网膜疾病，如果不及早治疗，会对眼睛血管造成损伤，是导致视力受损或失明的主要原因。由于眼睛结构复杂，手动检测糖尿病视网膜病变耗时且容易出现人为错误。方法&；结果：人们提出了各种自动技术来从眼底图像中检测糖尿病视网膜病变。然而，这些技术在捕捉糖尿病视网膜病变的复杂特征方面能力有限，尤其是在早期阶段。在这项研究中，我们提出了一种使用卷积神经网络（CNN）模型检测糖尿病视网膜病变的新方法。所提出的模型使用两种不同的深度学习（DL）模型Resnet50和Inceptionv3提取特征，并在将它们输入CNN进行分类之前将它们连接起来。所提出的模型是在公开可用的眼底图像数据集上进行评估的。实验结果表明，与最先进的方法相比，所提出的CNN模型实现了更高的准确性、敏感性、特异性、精密度和f1分数，分别为96.85%、99.28%、98.92%、96.46%和98.65%。

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分钟内获得全文求助全文

来源期刊

IEEE Journal of Translational Engineering in Health and Medicine-Jtehm Engineering-Biomedical Engineering

CiteScore

7.40

自引率

2.90%

发文量

审稿时长

27 weeks

期刊介绍： The IEEE Journal of Translational Engineering in Health and Medicine is an open access product that bridges the engineering and clinical worlds, focusing on detailed descriptions of advanced technical solutions to a clinical need along with clinical results and healthcare relevance. The journal provides a platform for state-of-the-art technology directions in the interdisciplinary field of biomedical engineering, embracing engineering, life sciences and medicine. A unique aspect of the journal is its ability to foster a collaboration between physicians and engineers for presenting broad and compelling real world technological and engineering solutions that can be implemented in the interest of improving quality of patient care and treatment outcomes, thereby reducing costs and improving efficiency. The journal provides an active forum for clinical research and relevant state-of the-art technology for members of all the IEEE societies that have an interest in biomedical engineering as well as reaching out directly to physicians and the medical community through the American Medical Association (AMA) and other clinical societies. The scope of the journal includes, but is not limited, to topics on: Medical devices, healthcare delivery systems, global healthcare initiatives, and ICT based services; Technological relevance to healthcare cost reduction; Technology affecting healthcare management, decision-making, and policy; Advanced technical work that is applied to solving specific clinical needs.