Ensemble Diabetic Retinopathy Detection in 2-D Color Fundus Retina Scan

IF 1.9 4区计算机科学 Q3 TELECOMMUNICATIONS

Wireless Personal Communications Pub Date : 2024-07-30 DOI:10.1007/s11277-024-11363-1

Himanshu Jindal, Shruti Jain, Akshit Aggarwal

引用次数: 0

Abstract

Diabetic Retinopathy (DR) is a burgeoning malady in Asian territories. DR causes 5–7% of the total blindness throughout the region. The main aim of this research is to determine whether a patient is suffering from DR or not by the dint of 2-D color fundus retina scans. In this paper, authors have proposed a GUI-based technique an Ensemble Diabetic Retinopathy Detection (EDRD). This method helps in detecting 2D color fundus scans with an efficient approach for finding DR-affected persons within a few seconds using ensemble techniques of CNN and RLU. The visual geometry group (VGG-19) model and adaptive moment estimation optimizer are used for training and reducing error for the developed technique. A maximum accuracy of 92% was obtained for an 80% training set with a 0.001 learning rate and 25 batch size. The proposed research contribution definitively detects whether the given OCT scan with an efficient approach for finding DR-affected persons within a few seconds.

Abstract Image

查看原文本刊更多论文

二维彩色眼底视网膜扫描中的糖尿病视网膜病变集合检测

糖尿病视网膜病变（DR）是亚洲地区的一种新兴疾病。在整个亚洲地区，5%-7%的失明是由糖尿病引起的。这项研究的主要目的是通过二维彩色眼底视网膜扫描来确定患者是否患有糖尿病视网膜病变。在本文中，作者提出了一种基于图形用户界面的技术--组合式糖尿病视网膜病变检测（EDRD）。该方法使用 CNN 和 RLU 的集合技术，以高效的方法检测二维彩色眼底扫描，从而在几秒钟内找到受 DR 影响的人。视觉几何组（VGG-19）模型和自适应矩估计优化器用于训练和减少所开发技术的误差。在学习率为 0.001、批量规模为 25 的情况下，80% 的训练集获得了 92% 的最高准确率。所提出的研究成果能在几秒钟内通过有效方法明确检测给定的 OCT 扫描是否能找到受 DR 影响的人。

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

Wireless Personal Communications 工程技术-电信学

CiteScore

5.80

自引率

9.10%

发文量

663

审稿时长

6.8 months

期刊介绍： The Journal on Mobile Communication and Computing ... Publishes tutorial, survey, and original research papers addressing mobile communications and computing; Investigates theoretical, engineering, and experimental aspects of radio communications, voice, data, images, and multimedia; Explores propagation, system models, speech and image coding, multiple access techniques, protocols, performance evaluation, radio local area networks, and networking and architectures, etc.; 98% of authors who answered a survey reported that they would definitely publish or probably publish in the journal again. Wireless Personal Communications is an archival, peer reviewed, scientific and technical journal addressing mobile communications and computing. It investigates theoretical, engineering, and experimental aspects of radio communications, voice, data, images, and multimedia. A partial list of topics included in the journal is: propagation, system models, speech and image coding, multiple access techniques, protocols performance evaluation, radio local area networks, and networking and architectures. In addition to the above mentioned areas, the journal also accepts papers that deal with interdisciplinary aspects of wireless communications along with: big data and analytics, business and economy, society, and the environment. The journal features five principal types of papers: full technical papers, short papers, technical aspects of policy and standardization, letters offering new research thoughts and experimental ideas, and invited papers on important and emerging topics authored by renowned experts.