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

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

Masquerading disease of macular telangiectasia type 2 - MacTel Project Report No 11.

Ophthalmology. Retina·2026

Same author

Automated Deep Learning Quantification of Avascular Area and Intravitreal Neovascularization in Retinal Flatmounts of Rodent Oxygen-Induced Retinopathy Models.

Translational vision science & technology·2026

Same author

A fatty acid amide activates myeloid cells and improves neurovascular outcomes in retinal degeneration.

Nature neuroscience·2026

Same author

Quantitative Swept-Source Optical Coherence Tomography Angiography Indicators of Neurovascular Dysfunction in Alzheimer Disease.

JAMA ophthalmology·2026

Same author

Mobile-Based Artificial Intelligence and Ocular Surface Malignancies.

JAMA ophthalmology·2026

Same author

Characterization of vascular tortuosity throughout the murine oxygen-induced retinopathy model of ischemic retinopathy.

JCI insight·2026

Search research articles

相关实验视频

Updated: May 13, 2025

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Published on: May 26, 2023

增强的斑点长长眼病2型检测:利用自我监督的学习和合奏模型.

Shahrzad Gholami¹, Lea Scheppke², Meghana Kshirsagar¹

¹AI for Good Research Lab, Microsoft, Redmond, Washington.

Ophthalmology science

|April 14, 2025

概括

此摘要是机器生成的。

集体深度学习方法使用OCT成像准确地检测到2型黄斑端膜切除症 (MacTel),即使具有有限的标记数据. 将自主监督学习与合体方法相结合,可以增强分类和解释.

关键词:

深度学习是一种深度学习.组合模型组合模型斑点远距离切除症2型 2型海洋和海域国家/地区成像技术自主监督学习学习

更多相关视频

Detecting Abnormalities in Choroidal Vasculature in a Mouse Model of Age-related Macular Degeneration by Time-course Indocyanine Green Angiography

Detecting Abnormalities in Choroidal Vasculature in a Mouse Model of Age-related Macular Degeneration by Time-course Indocyanine Green Angiography

Published on: February 19, 2014

Author Spotlight: Overcoming Anti-VEGF Resistance Through Advanced Vascular Morphology Assessment in Choroidal Neovascularization

Author Spotlight: Overcoming Anti-VEGF Resistance Through Advanced Vascular Morphology Assessment in Choroidal Neovascularization

Published on: August 11, 2023

相关实验视频

Last Updated: May 13, 2025

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Published on: May 26, 2023

Detecting Abnormalities in Choroidal Vasculature in a Mouse Model of Age-related Macular Degeneration by Time-course Indocyanine Green Angiography

Detecting Abnormalities in Choroidal Vasculature in a Mouse Model of Age-related Macular Degeneration by Time-course Indocyanine Green Angiography

Published on: February 19, 2014

Author Spotlight: Overcoming Anti-VEGF Resistance Through Advanced Vascular Morphology Assessment in Choroidal Neovascularization

Author Spotlight: Overcoming Anti-VEGF Resistance Through Advanced Vascular Morphology Assessment in Choroidal Neovascularization

Published on: August 11, 2023

科学领域:

眼科医生眼科眼科
医疗成像医学成像
人工智能的人工智能

背景情况:

斑点远视症 (MacTel) 2型是一种影响中心视力的视网膜疾病.
准确检测MacTel类型2对于及时诊断和管理至关重要.
光学连贯断层扫描 (OCT) 是视网膜疾病的关键成像方式.

研究的目的:

开发和评估基于集体的深度学习模型,用于在OCT图像上检测MacTel类型2.
评估深度学习模型在识别MacTel类型2时的可解释性.
为了比较模型的性能与人类专家评分器.

主要方法:

来自麦克泰尔注册和华盛顿大学的5200个OCT扫描的回顾性分析.
使用监督和自我监督学习 (SSL) 培训个人分类模型.
组合单个模型并使用AUROC,AUPRC,精度,灵敏度和特异性来评估性能.

主要成果:

整体模型的AUROC为0.972和AUPRC为0.967,与人类专家相似.
观察到高精度 (91.7%),灵敏度 (0.905) 和特异性 (0.925),尽管有限的标记训练数据 (10%).
个别的模特没有达到合奏的表现水平.

结论:

集成深度学习模型,特别是与SSL相结合时,可以准确和可解释地检测MacTel类型 2.
SSL有效地利用未标记的数据,证明在有限的数据集中对罕见疾病检测有好处.
这种方法有望改善MacTel2型诊断和患者护理.