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

Diabetic Retinopathy

Diabetic Retinopathy

DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...

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

From generalization to precision: A large domain-specific pretrained model for specialized medical tasks.

Cell reports. Medicine·2026

Same author

Automated diagnosis of keratitis from low-quality slit-lamp images using an improved generative adversarial network.

NPJ digital medicine·2026

Same author

Development of PROTACs for targeted degradation of oncogenic TRK fusions.

RSC chemical biology·2026

Same author

AMHF-TP: Multifunctional therapeutic peptides prediction based on multi-granularity hierarchical features.

Quantitative biology (Beijing, China)·2026

Same author

Evaluating reasoning large language models with human-like thinking in ophthalmic question answering.

BMJ open ophthalmology·2026

Same author

The APEXTAC System for Ligand-Guided Proximity Labeling.

Chembiochem : a European journal of chemical biology·2025

Search research articles

相关实验视频

Updated: Jun 27, 2026

Smartphone Fundus Photography

Smartphone Fundus Photography

Published on: July 6, 2017

使用元学习推广基于智能手机的角质炎查:一项多中心研究

Zhongwen Li¹, Yangyang Wang¹, Kuan Chen²

¹Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Institute, Ningbo Eye Hospital, Wenzhou Medical University, Ningbo 315040, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China.

Journal of biomedical informatics

|September 7, 2024

概括

此摘要是机器生成的。

一个新的meta-learning框架,即 cosine最接近的中心基学习 (CNCML),可以使用智能手机进行有效的角质炎查. 这种方法通过利用裂纹灯图像知识,在有限的智能手机数据中实现了高精度,提高了角膜失明检测的可访问性.

关键词:

深度学习是一种深度学习.脊髓炎是一种炎.超级学习 (Meta learning) 是一种超级学习.计量学学习的学习方法一个裂灯.一个智能手机的智能手机.

更多相关视频

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

$Subjective Refraction Test Using a Smartphone for Vision Screening$

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

相关实验视频

Last Updated: Jun 27, 2026

Smartphone Fundus Photography

Smartphone Fundus Photography

Published on: July 6, 2017

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

$Subjective Refraction Test Using a Smartphone for Vision Screening$

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

科学领域:

眼科医生眼科眼科
人工智能的人工智能
医疗成像医学成像

背景情况:

角膜炎是全球角膜失明的主要原因.
早期发现和转诊对于改善患者的治疗结果至关重要.
智能手机在服务不足的地区提供了炎查的潜力,但数据稀缺性挑战了传统的深度学习.

研究的目的:

为基于智能手机的角质炎查提出一个元学习框架,即基于近心点的CNCML (cosine closest centroid-based metric learning).
开发一个强大的模型,尽管智能手机数据有限,利用从灯图像的先前知识.

主要方法:

从3个临床中心使用13009张裂纹灯和4075张智能手机照片开发和评估CNCML.
训练有素的CNCML与来自HUAWEI智能手机的不同小数据集 (0-20图像/类) 来模拟现实世界的稀缺性.
在内部和外部智能手机数据集 (VIVO,XIAOMI) 上评估性能,并与传统的深度学习模型进行比较.

主要成果:

在每个类中,CNCML只用15个智能手机图像实现了高精度 (83.15%-89.99%) 和宏观AUC (0.95-0.98).
在智能手机数据集上,CNCML在准确性方面超过了传统的深度学习模型0.56%至9.65%.
证明了快速学习能力和在最少的训练样本下表现出色.

结论:

即使数据有限,CNCML也提供了使用智能手机查角膜炎的可行解决方案.
这种超学习方法有助于智能炎检测从专业设备转向无处不在的设备.
提高了炎查的便利性和有效性,特别是在偏远或服务不足的地区.