Hybrid adaptive deep learning classifier for early detection of diabetic retinopathy using optimal feature extraction and classification.

IF 1.8 Q4 ENDOCRINOLOGY & METABOLISM
Journal of Diabetes and Metabolic Disorders Pub Date : 2023-04-14 eCollection Date: 2023-06-01 DOI:10.1007/s40200-023-01220-6
S V Hemanth, Saravanan Alagarsamy
{"title":"Hybrid adaptive deep learning classifier for early detection of diabetic retinopathy using optimal feature extraction and classification.","authors":"S V Hemanth, Saravanan Alagarsamy","doi":"10.1007/s40200-023-01220-6","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Diabetic retinopathy (DR) is one of the leading causes of blindness. It is important to use a comprehensive learning method to identify the DR. However, comprehensive learning methods often rely heavily on encrypted data, which can be costly and time consuming. Also, the DR function is not displayed and is scattered in the high-definition image below.</p><p><strong>Methods: </strong>Therefore, learning how to distribute such DR functions is a big challenge. In this work, we proposed a hybrid adaptive deep learning classifier for early detection of diabetic retinopathy (HADL-DR). First, we provide an improved multichannel-based generative adversarial network (MGAN) with semi-maintenance to detect blood vessels segmentation.</p><p><strong>Results: </strong>By reducing the reliance on the encoded data, the following high-resolution images can be used to detect the indivisible features of some semi-observed MGAN references. Scale invariant feature transform (SIFT) function is then extracted and the best function is selected using the improved sequential approximation optimization (SAO) algorithm. After that, a hybrid recurrent neural network with long short-term memory (RNN-LSTM) is utilized for DR classification. The proposed RNN-LSTM classifier evaluated through standard benchmark Kaggle and Messidor datasets.</p><p><strong>Conclusion: </strong>Finally, the simulation results are compared with the existing state-of-art classifiers in terms of accuracy, precision, recall, f-measure and area under cover (AUC), it is seen that more successful results are obtained.</p>","PeriodicalId":15635,"journal":{"name":"Journal of Diabetes and Metabolic Disorders","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10225400/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Diabetes and Metabolic Disorders","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s40200-023-01220-6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/6/1 0:00:00","PubModel":"eCollection","JCR":"Q4","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives: Diabetic retinopathy (DR) is one of the leading causes of blindness. It is important to use a comprehensive learning method to identify the DR. However, comprehensive learning methods often rely heavily on encrypted data, which can be costly and time consuming. Also, the DR function is not displayed and is scattered in the high-definition image below.

Methods: Therefore, learning how to distribute such DR functions is a big challenge. In this work, we proposed a hybrid adaptive deep learning classifier for early detection of diabetic retinopathy (HADL-DR). First, we provide an improved multichannel-based generative adversarial network (MGAN) with semi-maintenance to detect blood vessels segmentation.

Results: By reducing the reliance on the encoded data, the following high-resolution images can be used to detect the indivisible features of some semi-observed MGAN references. Scale invariant feature transform (SIFT) function is then extracted and the best function is selected using the improved sequential approximation optimization (SAO) algorithm. After that, a hybrid recurrent neural network with long short-term memory (RNN-LSTM) is utilized for DR classification. The proposed RNN-LSTM classifier evaluated through standard benchmark Kaggle and Messidor datasets.

Conclusion: Finally, the simulation results are compared with the existing state-of-art classifiers in terms of accuracy, precision, recall, f-measure and area under cover (AUC), it is seen that more successful results are obtained.

混合自适应深度学习分类器用于糖尿病视网膜病变的早期检测,使用最佳特征提取和分类。
目的:糖尿病视网膜病变(DR)是致盲的主要原因之一。使用综合学习方法来识别DR是很重要的。然而,综合学习方法通常严重依赖于加密数据,这可能是昂贵和耗时的。此外,DR功能没有显示,并且分散在下面的高清晰度图像中。方法:因此,学习如何分配这样的DR功能是一个巨大的挑战。在这项工作中,我们提出了一种用于糖尿病视网膜病变早期检测的混合自适应深度学习分类器(HADL-DR)。首先,我们提供了一种改进的基于多通道的半维护生成对抗性网络(MGAN)来检测血管分割。结果:通过减少对编码数据的依赖,以下高分辨率图像可以用于检测一些半观察到的MGAN参考文献的不可分割特征。然后提取尺度不变特征变换(SIFT)函数,并使用改进的逐次逼近优化(SAO)算法选择最佳函数。然后,利用具有长短期记忆的混合递归神经网络(RNN-LSTM)进行DR分类。所提出的RNN-LSTM分类器通过标准基准Kaggle和Messidor数据集进行了评估。结论:最后,将仿真结果与现有的分类器在准确度、精密度、召回率、f-measure和覆盖面积(AUC)方面进行了比较,可以看出获得了更成功的结果。
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
Journal of Diabetes and Metabolic Disorders
Journal of Diabetes and Metabolic Disorders Medicine-Internal Medicine
CiteScore
4.80
自引率
3.60%
发文量
210
期刊介绍: Journal of Diabetes & Metabolic Disorders is a peer reviewed journal which publishes original clinical and translational articles and reviews in the field of endocrinology and provides a forum of debate of the highest quality on these issues. Topics of interest include, but are not limited to, diabetes, lipid disorders, metabolic disorders, osteoporosis, interdisciplinary practices in endocrinology, cardiovascular and metabolic risk, aging research, obesity, traditional medicine, pychosomatic research, behavioral medicine, ethics and evidence-based practices.As of Jan 2018 the journal is published by Springer as a hybrid journal with no article processing charges. All articles published before 2018 are available free of charge on springerlink.Unofficial 2017 2-year Impact Factor: 1.816.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信