Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jan 7, 2026

Fabrication and Characterization of a Conformal Skin-like Electronic System for Quantitative, Cutaneous Wound Management
08:50

Fabrication and Characterization of a Conformal Skin-like Electronic System for Quantitative, Cutaneous Wound Management

Published on: September 2, 2015

9.4K

自动化伤口评估:基于卷积神经网络的移动应用程序,用于SINBAD分类系统.

Farideh Mostafavi1, Sujit Kumar Das2, Mohammad Reza Amini3

  • 1Department of Epidemiology, School of Public Health and Safety, Shahid Beheshti University of Medical Sciences, Shahid Shahriari Sq., Student Blvd., Valenjak, Tehran, 1983969411 Iran.

Journal of diabetes and metabolic disorders
|December 29, 2025
PubMed
概括

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Sparse multi-way DMDC for longitudinal classification in high dimension low sample size data.

BMC medical research methodology·2026
Same author

The Effect of <i>Moringa oleifera</i> on Body Weight and Blood Pressure: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

Food science & nutrition·2026
Same author

The Effect of Cranberry Consumption on Body Weight and Liver Enzymes: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

Food science & nutrition·2026
Same author

Determination of the Optimal Cut-Off Point of Anthropometric Indices to Predict the Risk of Metabolic Syndrome in Iranian Adult Population With Type 2 Diabetes Mellitus: A Cross-Sectional-Analytical Study.

Endocrinology, diabetes & metabolism·2026
Same author

Research map of global trends, hotspots, and emerging topics in cardiovascular disease: A bibliometric analysis.

Medicine·2026
Same author

Predicting Diabetic Foot Ulcer Outcomes: Machine Learning-Based Refinement of IWGDF-Approved Classifications for Outpatient Services.

Endocrinology, diabetes & metabolism·2026
Same journal

Clarification of poor adherence to treatment among patients with type 2 diabetes in Iran: the magnitude of the problem and the its determinants.

Journal of diabetes and metabolic disorders·2026
Same journal

Are diabetologists against metabolic surgery?

Journal of diabetes and metabolic disorders·2026
Same journal

Socioeconomic inequalities and trends in the prevalence of childhood obesity phenotypes in Iran from 2000 to 2030.

Journal of diabetes and metabolic disorders·2026
Same journal

Hybrid deep learning models for diabetic retinopathy stage classification using fundus images.

Journal of diabetes and metabolic disorders·2026
Same journal

Heart rate nondipping pattern and left atrial remodeling as a marker of cardiac target organ damage in patients with type 2 diabetes.

Journal of diabetes and metabolic disorders·2026
Same journal

Association between serum vitamin D levels and peri-implant diseases.

Journal of diabetes and metabolic disorders·2026
查看所有相关文章
此摘要是机器生成的。

一个新的移动应用程序使用MobileNetV3小自动分类糖尿病足 (DFU) 组件使用SINBAD系统. 这种高效的工具可以改善DFU在临床环境中的评估.

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算生物学 计算生物学

背景情况:

  • 糖尿病足 (DFU) 评估对于临床决策至关重要,但往往缺乏专家访问.
  • SINBAD系统是DFU分类的标准.

研究的目的:

  • 开发和评估使用轻量级卷积神经网络 (CNN) 进行自动化DFU分类的移动应用程序.
  • 评估MobileNetV3 Small在为DFU分类五个SINBAD组件中的性能.

主要方法:

  • 使用了996张临床医生标记的DFU图像的数据集.
  • 一个MobileNetV3小模型被训练来分类五个SINBAD组件.
  • 使用准确度,F1分数,精度,回忆和AUC来评估性能,并与VGG16,ResNet50和DenseNet121.1进行比较.

主要成果:

  • 移动网络V3 小小在细菌感染 (93.1%),区域 (89.8%) 和神经病变 (86.2%) 中获得了高F1分,记忆力很好.
  • 对于缺血和深度,MobileNetV3 Small显示了适度的F1得分 (74.4%,61.6%) 和AUC (84.3%,80.3%),表现优于VGG16.
  • 紧的MobileNetV3小型号显示了与较大型号相比或超过的召回能力,适合敏感检测.
关键词:
卷积神经网络是一种卷积神经网络.糖尿病足部 糖尿病足部移动网络V3 小小的辛巴德 (SINBAD) 是一个

相关实验视频

Last Updated: Jan 7, 2026

Fabrication and Characterization of a Conformal Skin-like Electronic System for Quantitative, Cutaneous Wound Management
08:50

Fabrication and Characterization of a Conformal Skin-like Electronic System for Quantitative, Cutaneous Wound Management

Published on: September 2, 2015

9.4K

结论:

  • 移动NetV3小提供了一个实用和高效的解决方案,以移动为基础的DFU评估.
  • 该应用程序的强大的回忆和紧的架构使其在资源有限的设置中实现部署,以实现一致的SINBAD分类.