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

Differences in macular structure and microvasculature between high myopia and non-high myopia.

Frontiers in medicine·2025
Same author

A 43-Year-Old Man with a 30-Year History of a Retained Glass Intraocular Foreign Body Presenting with Retinal Detachment.

The American journal of case reports·2025
Same author

A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children.

NPJ digital medicine·2024
Same author

Correction: From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning.

PLOS digital health·2023
Same author

Six-Year Incidence and Risk Factors for Primary Open-Angle Glaucoma and Ocular Hypertension: The Singapore Epidemiology of Eye Diseases Study.

Ophthalmology. Glaucoma·2023
Same author

Assessment of anxiety and depression in patients with Posner-Schlossman syndrome.

BMC ophthalmology·2023

相关实验视频

Updated: Jul 12, 2025

Author Spotlight: Anterior HR-OCT as a Non-Invasive Tool for Characterizing Ocular Surface Squamous Neoplasia
06:15

Author Spotlight: Anterior HR-OCT as a Non-Invasive Tool for Characterizing Ocular Surface Squamous Neoplasia

Published on: August 9, 2024

1.2K

基于深度学习的前段OCT参数的量化.

Zhi Da Soh1,2, Mingrui Tan3, Monisha Esther Nongpiur1,4

  • 1Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.

Ophthalmology science
|October 23, 2023
PubMed
概括
此摘要是机器生成的。

一个新的深度学习算法在OCT扫描中自动化了脑膜刺激注释和前腔结构细分. 这一进步提高了眼睛测量的精度和效率,无论是在开角眼睛还是闭角眼睛.

关键词:
关闭角度的角度关闭.前腔室的测量结果在前段的OCT (ASOCT) 中.深度学习是一种深度学习.维桑特 ASOCT 的时间

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
00:09

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

6.9K

相关实验视频

Last Updated: Jul 12, 2025

Author Spotlight: Anterior HR-OCT as a Non-Invasive Tool for Characterizing Ocular Surface Squamous Neoplasia
06:15

Author Spotlight: Anterior HR-OCT as a Non-Invasive Tool for Characterizing Ocular Surface Squamous Neoplasia

Published on: August 9, 2024

1.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
00:09

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

6.9K

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:

  • 前段光学连贯性断层扫描 (ASOCT) 对于评估眼睛结构至关重要.
  • 精确的标注的硬膜刺激 (SS) 和前腔 (AC) 结构的细分对于青光眼的诊断和管理至关重要.
  • 手动细分是耗时的,并且受观察者之间的变化影响.

研究的目的:

  • 开发和验证深度学习算法,用于ASOCT扫描中的自动SS注释和AC结构细分.
  • 为了能够精确测量AC,虹膜和角度宽度参数.
  • 减少主观性,提高ASOCT基于眼睛测量的效率.

主要方法:

  • 使用CycleGAN. 的图像对比度增强.
  • 一种热图回归方法,用于SS注释的粗细框架.
  • 一个整体网络 (U-Net,全分辨率剩余网络,全分辨率U-Net) 用于结构细分.
  • 算法衍生的测量与手动注释的比较 (基本真相).

主要成果:

  • 该算法在SS注释中实现了高精度 (欧几里德距离:124.7μm,ICC≥0.95,错误率:3.3%).
  • 卓越的细分性能,角膜,虹膜和AC的Dice相似系数≥0.91.
  • 角度宽度测量显示与手动方法有很强的一致性 (≥95%在一致性范围内,ICC 0.71-0.87).
  • 与半自动程序相比,算法测量显示的变化较小.

结论:

  • 一个经过验证的深度学习算法有效地在ASOCT扫描中自动化SS注释和AC结构细分.
  • 该算法在开角眼睛和闭角眼睛中表现得与人类专家相比.
  • 这项技术显著减少了测量时间和主观性,有助于临床实践.