Diabetic Foot Ulcers Detection Model Using a Hybrid Convolutional Neural Networks-Vision Transformers.

IF 3 3区 医学 Q1 MEDICINE, GENERAL & INTERNAL
Abdul Rahaman Wahab Sait, Ramprasad Nagaraj
{"title":"Diabetic Foot Ulcers Detection Model Using a Hybrid Convolutional Neural Networks-Vision Transformers.","authors":"Abdul Rahaman Wahab Sait, Ramprasad Nagaraj","doi":"10.3390/diagnostics15060736","DOIUrl":null,"url":null,"abstract":"<p><p><b>Background:</b> Diabetic foot ulcers (DFUs) are severe and common complications of diabetes. Early and accurate DFUs classification is essential for effective treatment and prevention of severe complications. The existing DFUs classification methods have certain limitations, including limited performance, poor generalization, and lack of interpretability, restricting their use in clinical settings. <b>Objectives:</b> To overcome these limitations, this study proposes an innovative model to achieve robust and interpretable DFUs classification. <b>Methodology:</b> The proposed DFUs classification integrates MobileNet V3-SWIN, LeViT-Peformer, Tensor-based feature fusion, and ensemble splines-based Kolmogorov-Arnold Networks (KANs) with Shapley Additive exPlanations (SHAP) values to classify DFUs severities into ischemia and infection classes. In order to train and generalize the proposed model, the authors utilized the DFUs challenge (DFUC) 2021 and 2020 datasets. <b>Findings:</b> The proposed model achieved state-of-the-art performance, outperforming the existing approaches by obtaining an average accuracy of 98.7%, precision of 97.3%, recall of 97.4%, and F1-score of 97.3% on DFUC 2021. On DFUC 2020, it maintained a robust generalization accuracy of 96.9%, demonstrating superiority over standalone and baseline models. The study findings have significant implications for research and clinical practice. The findings offer an effective platform for scalable and explainable automated DFUs treatment and management, improving patient outcomes and clinical practices.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 6","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11941693/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diagnostics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3390/diagnostics15060736","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Diabetic foot ulcers (DFUs) are severe and common complications of diabetes. Early and accurate DFUs classification is essential for effective treatment and prevention of severe complications. The existing DFUs classification methods have certain limitations, including limited performance, poor generalization, and lack of interpretability, restricting their use in clinical settings. Objectives: To overcome these limitations, this study proposes an innovative model to achieve robust and interpretable DFUs classification. Methodology: The proposed DFUs classification integrates MobileNet V3-SWIN, LeViT-Peformer, Tensor-based feature fusion, and ensemble splines-based Kolmogorov-Arnold Networks (KANs) with Shapley Additive exPlanations (SHAP) values to classify DFUs severities into ischemia and infection classes. In order to train and generalize the proposed model, the authors utilized the DFUs challenge (DFUC) 2021 and 2020 datasets. Findings: The proposed model achieved state-of-the-art performance, outperforming the existing approaches by obtaining an average accuracy of 98.7%, precision of 97.3%, recall of 97.4%, and F1-score of 97.3% on DFUC 2021. On DFUC 2020, it maintained a robust generalization accuracy of 96.9%, demonstrating superiority over standalone and baseline models. The study findings have significant implications for research and clinical practice. The findings offer an effective platform for scalable and explainable automated DFUs treatment and management, improving patient outcomes and clinical practices.

背景:糖尿病足溃疡(DFUs)是严重而常见的糖尿病并发症。早期准确的 DFUs 分类对于有效治疗和预防严重并发症至关重要。现有的 DFUs 分类方法存在一定的局限性,包括性能有限、通用性差和缺乏可解释性,限制了它们在临床环境中的应用。研究目的:为了克服这些局限性,本研究提出了一种创新模型,以实现稳健且可解释的 DFUs 分类。方法:所提出的 DFUs 分类方法整合了 MobileNet V3-SWIN、LeViT-Peformer、基于张量的特征融合以及基于柯尔莫哥洛夫-阿诺德网络(KANs)和 Shapley Additive exPlanations(SHAP)值的集合样条,将 DFUs 的严重程度分为缺血和感染两类。为了训练和推广所提出的模型,作者利用了 2021 年和 2020 年的 DFUs challenge(DFUC)数据集。研究结果在 DFUC 2021 数据集上,拟议模型的平均准确率为 98.7%,精确率为 97.3%,召回率为 97.4%,F1 分数为 97.3%,表现优于现有方法。在 DFUC 2020 上,它保持了 96.9% 的稳健泛化准确率,显示出优于独立模型和基线模型的性能。研究结果对研究和临床实践具有重要意义。研究结果为可扩展、可解释的 DFUs 自动治疗和管理提供了一个有效平台,可改善患者预后和临床实践。
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
Diagnostics
Diagnostics Biochemistry, Genetics and Molecular Biology-Clinical Biochemistry
CiteScore
4.70
自引率
8.30%
发文量
2699
审稿时长
19.64 days
期刊介绍: Diagnostics (ISSN 2075-4418) is an international scholarly open access journal on medical diagnostics. It publishes original research articles, reviews, communications and short notes on the research and development of medical diagnostics. There is no restriction on the length of the papers. Our aim is to encourage scientists to publish their experimental and theoretical research in as much detail as possible. Full experimental and/or methodological details must be provided for research articles.
×
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