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

Search research articles

相关实验视频

Updated: Jan 8, 2026

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

一个深度学习驱动的白内障查模型,来自多中心真实世界数据集.

Zhonghui Cui¹, Yu Cheng², Siqi Pan²

¹Department of Ophthalmology, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.

Frontiers in medicine

|December 15, 2025

概括

此摘要是机器生成的。

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

Comment on "Topical Combined 5-Fluorouracil & Calcipotriene for Actinic Keratosis and Superficial Keratinocyte Carcinoma: Modified Delphi Expert Panel Guidelines from ITSCC".

Journal of the American Academy of Dermatology·2026

Same author

An IGF2BP3-dependent metabolic circuit governs macrophage recruitment and immunosuppression in glioblastoma.

Cell reports·2026

Same author

RBFOX2 suppresses NETosis and glioma growth via 5hmC-dependent PDGFB decay.

Cell reports·2026

Same author

[Analysis of associated factors for the ectopic eruption of adjacent first permanent molars after stainless steel crown restoration of second primary molars].

Hua xi kou qiang yi xue za zhi = Huaxi kouqiang yixue zazhi = West China journal of stomatology·2026

Same author

Tumor-intrinsic B4GALNT3 expression drives a protective immune microenvironment in endometriosis-associated ovarian cancer.

Translational cancer research·2026

Same author

CDsyn: A comprehensive database for deleterious human synonymous variation prediction.

iScience·2026

这项研究开发了一个强大的人工智能模型用于白内障查,使用来自多个中心的多样化,现实世界的数据. 人工智能工具显示出高精度,提高了广泛的眼科查和预防失明的概括性.

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:

白内障是全球可逆失明的主要原因,需要早期检测.
现有的白内障查人工智能模型往往缺乏通用性,这是由于同质的,单一中心的训练数据.

研究的目的:

开发和验证用于白内障检测的可通用深度学习模型,使用大规模的多中心数据集.
为可靠的医疗人工智能系统建立一个方法框架.

主要方法:

一个深度学习模型在来自中国21个机构的22,094张裂变灯图像上受训.
采用了级联框架,包括自动化质量评估,混杂查 (例如,pterygium) 和差异诊断.
在这个框架内,评估了各种深度学习架构.

主要成果:

领先的模型在独立的白内障分类测试组中取得了高性能.
一个ResNet50-IBN模型显示了93.74%的准确性,97.74%的特异性和95.30%的AUC.
由于多中心,现实世界的数据训练,该模型被证明是强大的和可通用的.

结论:

在多样化的多中心数据上训练人工智能模型可以提高眼科查的稳定性和通用性.

关键词:

诊断白内障诊断白内障的诊断深度学习是一种深度学习.医疗图像分析分析多中心数据多中心数据现实世界的研究研究.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关实验视频

Last Updated: Jan 8, 2026

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

开发的模型是大规模查和预防失明的可靠工具.

这项研究为创建可靠的医学深度学习系统提供了蓝图.