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

Association between social support and health-related quality of life among Chinese rural elders in nursing homes: the mediating role of resilience.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2017
Same author

Pharmacotherapy of Apnea by Cannabimimetic Enhancement, the PACE Clinical Trial: Effects of Dronabinol in Obstructive Sleep Apnea.

Sleep·2017
Same author

Arylsulfatase B is reduced in prostate cancer recurrences.

Cancer biomarkers : section A of Disease markers·2017
Same author

C-reactive protein is a predictor of prognosis in renal cell carcinoma patients receiving tyrosine kinase inhibitors: A meta-analysis.

Clinica chimica acta; international journal of clinical chemistry·2017
Same author

Rapid generation of a novel DPP-4 inhibitor with long-acting properties: SAR study and PK/PD evaluation.

European journal of medicinal chemistry·2017
Same author

Right-to-left shunt may be prone to affect the white matter integrity of posterior circulation in migraine without aura.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2017
Same journal

Generalizable framework for multi-site bone density prediction using non-dominant wrist optical biomarkers.

Biomedical optics express·2026
Same journal

Erratum: Review of dynamic optical coherence tomography for intracellular motility [Invited]: errata.

Biomedical optics express·2026
Same journal

Digital-micromirror-device-based illumination strategies for background suppression in single-molecule localization microscopy.

Biomedical optics express·2026
Same journal

Synergistic combination of convective self-assembly and hollow core fiber for sensitive SERS detection of glucose molecules.

Biomedical optics express·2026
Same journal

Multimodal diagnostic network integrating infrared and mass spectra for lung cancer.

Biomedical optics express·2026
Same journal

Multimodal Optical Biosensing for Precision Medicine and Healthcare: Introduction to the feature issue.

Biomedical optics express·2026
查看所有相关文章

相关实验视频

Updated: Jul 21, 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

2.8K

深度学习网络具有可差异化的动态编程,用于视网膜OCT表面细分.

Hui Xie1, Weiyu Xu1, Ya Xing Wang2

  • 1Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA, USA.

Biomedical optics express
|July 27, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的深度学习方法,用于在光学相干断层扫描 (OCT) 图像中对视网膜表面进行细分. 该方法通过强制执行表面光滑度来提高准确性,这对于诊断诸如与年龄相关的黄斑变性和多发性硬化症等疾病至关重要.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

相关实验视频

Last Updated: Jul 21, 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

2.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 生物医学工程 生物医学工程

背景情况:

  • 由于边界较弱,在OCT图像中对多个表面进行细分是具有挑战性的.
  • 深度学习方法看起来很有前途,但在有限的医学培训数据下扎,阻碍了像表面光滑性这样的全球结构学习.

研究的目的:

  • 开发一个端到端的深度学习方法用于视网膜OCT表面细分.
  • 通过将U-Net与受约束可微分动态编程模块统一,明确强制表面光滑.

主要方法:

  • 一个U-Net架构与可差异化的动态编程模块集成,用于功能学习和细分.
  • 该方法利用下游模型优化的反来指导特征学习,并强制执行全球表面结构.

主要成果:

  • 拟议的方法在Duke AMD和JHU MS OCT数据集上实现了视网膜层细分的亚声素精度.
  • 平均绝对表面距离 (MASD) 误差分别为1.88 ± 1.96 μm和2.75 ± 0.94 μm.

结论:

  • 统一的深度学习和动态编程方法有效地细分了OCT视网膜表面.
  • 该方法展示了全球表面结构和光滑性的优越强制执行,从而达到高精度.