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

Glaucoma: Overview01:25

Glaucoma: Overview

570
Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...
570

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

Light-Driven C<sub>4</sub> Biosynthesis from CO<sub>2</sub> and H<sub>2</sub>O via Engineered Photocatalyst-Microbial Consortia.

Journal of the American Chemical Society·2026
Same author

Association between allergic diseases and influenza or pneumonia incidence among children in the United States: A nationally representative study.

Medicine·2025
Same author

Personalized Morphological Brain Network Analysis for Temporal Lobe Epilepsy: Combining Cortical Thickness and Volume Features.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Openness-aware multi-prototype learning for open set medical diagnosis.

Medical image analysis·2025
Same author

Category-specific unlabeled data risk minimization for ultrasound semi-supervised segmentation.

Medical image analysis·2025
Same author

An intra- and inter-class context and consistency network for supervised and semi-supervised blastocyst segmentation.

Scientific reports·2025

相关实验视频

Updated: Jul 2, 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

通过利用正常的OCT图像与知识转移学习来开发具有成本效益和青光眼特异性的模型.

Kai Liu1,2,3, Jicong Zhang1,2,4

  • 1School of Biological Science and Medical Engineering, Beihang University, Beijing, 100083, China.

Biomedical optics express
|February 29, 2024
PubMed
概括

本研究介绍了一种知识转移学习模型,以使用正常的OCT图像来改善眼的监测. 该模型有效地转移知识,缩小了青光眼检测的性能差距.

更多相关视频

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents
10:10

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Published on: February 15, 2022

1.4K
A Model of Glaucoma Induced by Circumlimbal Suture in Rats and Mice
07:00

A Model of Glaucoma Induced by Circumlimbal Suture in Rats and Mice

Published on: October 5, 2018

10.4K

相关实验视频

Last Updated: Jul 2, 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
Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents
10:10

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Published on: February 15, 2022

1.4K
A Model of Glaucoma Induced by Circumlimbal Suture in Rats and Mice
07:00

A Model of Glaucoma Induced by Circumlimbal Suture in Rats and Mice

Published on: October 5, 2018

10.4K

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:

  • 对视力保护而言,对青光眼的进展监测至关重要.
  • 目前的深度学习模型在早期检测方面表现出色,但由于没有足够的注释数据,在确认的玻璃眼病例中扎.
  • 充分利用丰富,低成本的正常光学连贯断层扫描 (OCT) 图像来检测青光眼症是一个知识转移的挑战.

研究的目的:

  • 开发一种知识转移学习模型,利用正常的OCT图像来改善对青光眼的进展监测.
  • 为了有效的知识转移,在正常和青光眼领域之间建立明确的关系.
  • 解决在检测确诊青光眼患者中的绩效差距.

主要方法:

  • 一种新的知识转移学习模式,采用三步对抗策略,在培训期间整合青光眼领域信息.
  • 在输出和编码空间中,利用不同级别的共享功能的一种多层战略.
  • 开发和使用TongRen OCT DrDeramus数据集,包括像素级注释的OCT DrDeramus图像和诊断数据.

主要成果:

  • 与无监督和混合培训策略相比,拟议的模型表现出优异的表现,mIoU分别增加了5.28%和5.77%.
  • 与完全监督的模型相比,性能差距显著缩小,mIoU仅下降了1.01%.
  • 该模型有效地提取了与眼有关的特征,有助于跟踪疾病的进展.

结论:

  • 建议的知识转移学习模型通过有效利用正常的OCT图像数据,为眼监测提供了可行的解决方案.
  • 这种方法有助于弥合在检测青光眼确诊患者中的绩效差距,为临床应用提供了有价值的工具.
  • 该模型有助于提取关键的青光眼特征,支持更好的疾病进展跟踪和管理.