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

Choriocapillaris Flow-Enriched Prediction of Retinal Sensitivity Using OCT-Derived Biomarkers in Intermediate Age-Related Macular Degeneration.

Journal of clinical medicine·2026
Same author

I-SCREEN: Development of an AI-based infrastructure for community-wide screening and prediction of progression in age-related macular degeneration providing accessible shared care.

Eye (London, England)·2026
Same author

Using adaptive optics to assess hyporeflective clump speed and size in age-related macular degeneration in the PINNACLE Study. (PINNACLE Study Report 6).

Eye (London, England)·2025
Same author

ROQUS: a retinal OCT quality and usability score.

Biomedical optics express·2025
Same author

Superficial Retinal Intercapillary Oxygen Diffusion and Perfusion Deficit Alterations in Patients With Coronary Artery Disease.

Investigative ophthalmology & visual science·2025
Same author

Long-term effects of drusenoid pigment epithelial detachment on the retina and the choroid.

Canadian journal of ophthalmology. Journal canadien d'ophtalmologie·2025

相关实验视频

Updated: Jun 12, 2025

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

2.7K

预训练用于视网膜OCT的3D图像细分模型,使用基于denoising的自我监督学习.

Antoine Rivail1,2, Teresa Araújo1, Ursula Schmidt-Erfurth3

  • 1Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria.

Biomedical optics express
|September 19, 2024
PubMed
概括

自主监督学习 (SSL) 使用图像修复和解密技术可以预训练3D网络用于视网膜OCT细分. 这种方法提高了流体细分性能,减少了注释需求.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
Subretinal Transplantation of Human Embryonic Stem Cell Derived-retinal Pigment Epithelial Cells into a Large-eyed Model of Geographic Atrophy
11:03

Subretinal Transplantation of Human Embryonic Stem Cell Derived-retinal Pigment Epithelial Cells into a Large-eyed Model of Geographic Atrophy

Published on: January 22, 2018

10.0K

相关实验视频

Last Updated: Jun 12, 2025

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

2.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
Subretinal Transplantation of Human Embryonic Stem Cell Derived-retinal Pigment Epithelial Cells into a Large-eyed Model of Geographic Atrophy
11:03

Subretinal Transplantation of Human Embryonic Stem Cell Derived-retinal Pigment Epithelial Cells into a Large-eyed Model of Geographic Atrophy

Published on: January 22, 2018

10.0K

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:

  • 深度学习自动化了视网膜生物标志物细分在光学一致性断层扫描 (OCT) 临床研究和患者监测.
  • 目前的方法,如U-Nets,需要受监督的培训和广泛的,专家注释的数据集,这是很难和昂贵的.

研究的目的:

  • 调查3D自主监督学习 (SSL) 的有效性,使用预训练网络的图像恢复技术.
  • 提高视网膜CT的流体细分性能,减少对手册注释的依赖.

主要方法:

  • 探索了两个SSL方法:图像恢复和denoising,用于在大型3D OCT数据集上预训练3D网络.
  • 通过对两个不同的流体细分数据集进行微调来评估预训练的网络重量,这些数据集具有不同数量的训练数据.

主要成果:

  • 与传统的监督方法相比,这两种SSL方法都显著提高了流体细分性能.
  • 基于denoising的SSL在流体细分数据集上表现出卓越的结果,并实现了更快的预训练持续时间.
  • 采用SSL方法可以减少所需的注释,或提高细分精度.

结论:

  • 3D自主监督学习,特别是基于denoising的方法,为改善视网膜OCT的流体细分提供了可行和有效的策略.
  • 这种技术可以大大降低注释负担,提高眼科中自动细分的精度.
  • SSL为推进人工智能驱动的临床研究和视网膜成像中的患者监测提供了有前途的途径.