Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation

Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation

Clinical manifestationsPeripheral Arterial Disease (PAD) manifests through a range of symptoms, from the characteristic intermittent claudication to atypical presentations and severe complications in advanced stages. Intermittent claudication, a hallmark symptom of PAD, presents as exercise-induced muscle pain that typically resolves within minutes of rest. This pain is reproducible and stems from inadequate blood flow, leading to the accumulation of lactic acid produced during anaerobic...

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

Anatomy-guided weakly supervised learning framework for corneal nerve image denoising and enhancement.

Biomedical optics express·2026

Same author

Diabetic peripheral neuropathy identification using enface optical coherence tomography and multi-head attention deep learning algorithm.

Digital health·2026

Same author

Multi-frame fusion enhances analytical and diagnostic efficiency in corneal confocal microscopy.

Scientific reports·2025

Same author

ConNeCT: weakly supervised corneal confocal microscopy image inpainting network based on a diffusion model.

Biomedical optics express·2025

Same author

Automated program using convolutional neural networks for objective and reproducible selection of corneal confocal microscopy images.

Digital health·2025

Same author

Neutrophil-to-lymphocyte ratio is associated with diabetic peripheral neuropathy in type 2 diabetes patients.

Diabetes research and clinical practice·2017

Search research articles

相关实验视频

Updated: Apr 13, 2026

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

基于深度学习的自动化工具用于诊断糖尿病外围神经病变.

Qincheng Qiao^1,2, Juan Cao^1,3,4,5, Wen Xue^1,2

¹Department of Endocrinology and Metabolism, Qilu Hospital, Shandong University, Jinan, China.

|January 1, 2025

概括

一个新的深度学习工具自动化从角膜共聚焦显微镜 (CCM) 图像进行角膜神经纤维分析,用于早期发现糖尿病外围神经病变 (DPN). 这种自动化方法与手动分析具有很高的一致性,有助于DPN诊断.

关键词:

人工智能的人工智能是人工智能.角膜共聚焦显微镜角膜共聚焦显微镜深度学习是一种深度学习.糖尿病神经病变糖尿病神经病变

更多相关视频

Three-dimensional Imaging and Analysis of Mitochondria within Human Intraepidermal Nerve Fibers

Three-dimensional Imaging and Analysis of Mitochondria within Human Intraepidermal Nerve Fibers

Published on: September 29, 2017

An Ultrasonic Tool for Nerve Conduction Block in Diabetic Rat Models

An Ultrasonic Tool for Nerve Conduction Block in Diabetic Rat Models

Published on: October 20, 2017

相关实验视频

Last Updated: Apr 13, 2026

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

Three-dimensional Imaging and Analysis of Mitochondria within Human Intraepidermal Nerve Fibers

Three-dimensional Imaging and Analysis of Mitochondria within Human Intraepidermal Nerve Fibers

Published on: September 29, 2017

An Ultrasonic Tool for Nerve Conduction Block in Diabetic Rat Models

An Ultrasonic Tool for Nerve Conduction Block in Diabetic Rat Models

Published on: October 20, 2017

科学领域:

眼科医生眼科眼科
神经学神经学
医疗成像医学成像

背景情况:

糖尿病外围神经病变 (DPN) 是一种常见的糖尿病并发症,需要早期检测.
角膜共聚焦显微镜 (CCM) 为DPN诊断提供角膜神经纤维 (CNF) 的非侵入性评估.
现有的CNF分析方法存在局限性,需要自动化解决方案.

研究的目的:

开发和验证基于深度学习的自动化工具,用于从CCM图像中对CNF参数进行细分和量化.
评估自动化工具的性能与手动注释和ACCMetrics等现有方法相比.
评估该工具在早期DPN诊断方面的潜力.

主要方法:

训练和评估深度学习 (DL) 模型用于CCM图像细分.
开发了一种图像处理算法,用于自动提取和定量CNF形态参数.
使用手册注释,ACCMetrics,布兰德-阿尔特曼分析和类内相关系数 (ICC) 验证了该工具.

主要成果:

在CCM图像分割中,U2Net模型实现了最高的性能 (0.8115的mIoU).
与ACCMetrics相比,自动化工具与手动结果的一致性明显更高,用于CNF参数量化.
该工具实现了基于CNF形态的DPN分类的0.75曲线下的面积.

结论:

开发的基于DL的工具有效地对CCM图像中的CNF参数进行细分和量化.
这种自动化工具对早期诊断DPN有希望.
需要进一步的临床验证来确认这种工具的实际应用价值.