ViT-HHO:利用哈里斯-霍克优化技术检测糖尿病视网膜病变的优化视觉转换器

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES MethodsX Pub Date : 2024-10-23 DOI:10.1016/j.mex.2024.103018
Vishal Awasthi , Namita Awasthi , Hemant Kumar , Shubhendra Singh , Prabal Pratap Singh , Poonam Dixit , Rashi Agarwal
{"title":"ViT-HHO:利用哈里斯-霍克优化技术检测糖尿病视网膜病变的优化视觉转换器","authors":"Vishal Awasthi ,&nbsp;Namita Awasthi ,&nbsp;Hemant Kumar ,&nbsp;Shubhendra Singh ,&nbsp;Prabal Pratap Singh ,&nbsp;Poonam Dixit ,&nbsp;Rashi Agarwal","doi":"10.1016/j.mex.2024.103018","DOIUrl":null,"url":null,"abstract":"<div><div>Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.<ul><li><span>•</span><span><div>An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).</div></span></li><li><span>•</span><span><div>The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.</div></span></li><li><span>•</span><span><div>The model's generalization and robustness were demonstrated through comprehensive performance evaluations.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103018"},"PeriodicalIF":1.6000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization\",\"authors\":\"Vishal Awasthi ,&nbsp;Namita Awasthi ,&nbsp;Hemant Kumar ,&nbsp;Shubhendra Singh ,&nbsp;Prabal Pratap Singh ,&nbsp;Poonam Dixit ,&nbsp;Rashi Agarwal\",\"doi\":\"10.1016/j.mex.2024.103018\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.<ul><li><span>•</span><span><div>An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).</div></span></li><li><span>•</span><span><div>The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.</div></span></li><li><span>•</span><span><div>The model's generalization and robustness were demonstrated through comprehensive performance evaluations.</div></span></li></ul></div></div>\",\"PeriodicalId\":18446,\"journal\":{\"name\":\"MethodsX\",\"volume\":\"13 \",\"pages\":\"Article 103018\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"MethodsX\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2215016124004692\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"MethodsX","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215016124004692","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

糖尿病视网膜病变(DR)是全球视力受损的重要原因之一,因此必须及时、精确地检测以防止严重后果的发生。本研究提出了一种优化的视觉转换器(ViT)模型,该模型结合了哈里斯鹰优化(HHO)技术,以改进糖尿病视网膜病变(DR)的自动检测。ViT 架构利用自我注意机制捕捉视网膜图像中的局部和全局特征。此外,HHO 还优化了关键超参数,以最大限度地提高模型的性能。所提出的 ViT-HHO 模型在 APTOS-2019 和 IDRiD 数据集上取得了优异的性能。具体来说,它在 APTOS-2019 数据集上实现了 99.83 % 的准确率、99.78 % 的灵敏度、99.85 % 的特异性和 99.80 % 的 AUC-ROC,超越了传统的 CNN 和其他优化技术。该模型在 IDRiID 数据集上表现出很强的泛化能力,准确率达到 99.11%,AUC-ROC 达到 99.12%。该模型在 APTOS-2019 和 IDRiID 数据集上进行了验证,显示出卓越的准确性和 AUC-ROC 指标。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

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
ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization
Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.
  • An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).
  • The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.
  • The model's generalization and robustness were demonstrated through comprehensive performance evaluations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
MethodsX
MethodsX Health Professions-Medical Laboratory Technology
CiteScore
3.60
自引率
5.30%
发文量
314
审稿时长
7 weeks
期刊介绍:
期刊最新文献
Experimental optimization for synthesis of cerium-doped titanium dioxide nanoparticles by modified sol-gel process Correction methods and applications of ERT in complex terrain A method to enhance privacy preservation in cloud storage through a three-layer scheme for computational intelligence in fog computing Method for measuring the transpiration resistance of fruit and vegetables Deep learning-based classification of alfalfa varieties: A comparative study using a custom leaf image dataset
×
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