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

相关实验视频

Updated: Jan 11, 2026

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.2K

深度学习算法预测视网膜撕裂和脱离从光学连贯断层扫描.

Anish Salvi1, Yeabsira Mesfin2, Leo Arnal1

  • 1School of Medicine, Stanford University, Palo Alto, CA, USA.

Translational vision science & technology
|November 17, 2025
PubMed
概括

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

Evaluation of Large Language Models for Structured Data Extraction From Interstitial Lung Disease Clinical Notes: Comparative Study.

Journal of medical Internet research·2026
Same author

Postpartum Plasma-Derived Exosomes Confer Mitochondrial Stabilization and Neuroprotection against Ischemic Stroke.

Research square·2026
Same author

Prevalence and incidence of mental health disorders in patients with inherited retinal diseases: a population-based study.

Journal of AAPOS : the official publication of the American Association for Pediatric Ophthalmology and Strabismus·2026
Same author

Association Between Mental Health Disorders in Age-Related Macular Degeneration: A Cohort Study Using a Global Health Records Network.

Ophthalmic surgery, lasers & imaging retina·2026
Same author

The Role of Systemic Methotrexate on Preventing Proliferative Vitreoretinopathy Following Retinal Detachment Repair.

Ophthalmic surgery, lasers & imaging retina·2026
Same author

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

Advances in neural information processing systems·2026

这项研究开发了一个AI分类器,使用光学连贯断层扫描 (OCT) 图像来预测视网膜撕裂和脱落 (RT/RD) 的可能性. 该模型准确地识别了高风险患者,使得早期干预能够预防视力丧失.

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:

  • 视网膜撕裂和脱落 (RT/RD) 是导致视力丧失的主要原因.
  • 早期发现RT/RD对于有效治疗和维护视力至关重要.
  • 当前的诊断方法可能并不总是能够识别未来RT/RD高风险的患者.

研究的目的:

  • 开发和验证一个图像分类器,用于预测未来的RT/RD使用OCT的可能性.
  • 为RT/RD预后中的临床相关性提供像素级的解释.
  • 为了利用深度学习来识别易受预防治疗的高风险患者.

主要方法:

  • 一个卷积神经网络 (Inception-v4) 被训练在来自斯坦福研究库的OCT图像上.
  • 患者根据RT/RD状态和手术史进行分类.
  • 梯度加权类激活映射 (Grad-CAM) 用于生成热图以实现模型解释性.

主要成果:

  • 分类器实现了接收器运行特征曲线下的面积为0.87.
  • 平均精度为0.85,准确度为0.78.
  • 热图突出显示了与RT/RD风险相关的关键黄斑生物标志物,例如视网膜和视体引力.

更多相关视频

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy
08:22

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Published on: January 12, 2022

5.1K
In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
07:35

In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

Published on: April 21, 2022

2.6K

相关实验视频

Last Updated: Jan 11, 2026

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.2K
Application of Optical Coherence Tomography to a Mouse Model of Retinopathy
08:22

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Published on: January 12, 2022

5.1K
In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
07:35

In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

Published on: April 21, 2022

2.6K

结论:

  • 开发的二进制图像分类器准确地从OCT扫描中预测未来的RT/RD发展.
  • 深度学习算法识别了关键的生物标志物,从而能够及时进行预防性干预.
  • 这项技术提供了一种潜在的途径,可以预防风险人群的视力丧失.