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: Jul 10, 2025

Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

18.8K

半监督点一致性网络用于视网膜动脉/静脉分类.

Jingfei Hu1, Linwei Qiu1, Hua Wang1

  • 1School of Biological Science and Medical Engineering, Beihang University, Beijing, 100191, China; Hefei Innovation Research Institute, Beihang University, Hefei, 230012, Anhui, China.

Computers in biology and medicine
|November 22, 2023
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

Comparative study of three PCR-based copy number variant approaches, CFMSA, M-PCR, and MLPA, in 22q11.2 deletion syndrome.

Genetic testing and molecular biomarkers·2009
Same author

[Influence on electroacupuncture at "Qiangzhuang" acupoints for neuro-immune regulation of sub-acute aged rats].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2009
Same author

[Effects of killer immunoglobulin-like receptor and human leukocyte antigen class I ligand on the prognosis of related donor hematopoietic stem cell transplantation].

Zhongguo yi xue ke xue yuan xue bao. Acta Academiae Medicinae Sinicae·2009
Same author

[Treatment of nonunion of tibia with superficial peroneal vascular fascia pedicel tibiofibular periosteal flap].

Zhongguo xiu fu chong jian wai ke za zhi = Zhongguo xiufu chongjian waike zazhi = Chinese journal of reparative and reconstructive surgery·2009
Same author

[Expression, purification and activity analysis of BCG HSP70.].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2009
Same author

Comparison of diffusion-weighted with T2-weighted Imaging for detection of small hepatocellular carcinoma in cirrhosis: preliminary quantitative study at 3-T.

Academic radiology·2009

这项研究引入了一种新的半监督网络 (SPC-Net),用于准确的视网膜动脉/静脉分类. 它有效地解决了医疗成像深度学习的挑战,减少了对广泛标记数据的需求.

科学领域:

  • 医学图像分析 医学图像分析
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 眼科医生 眼科 眼科

背景情况:

  • 卷积神经网络 (CNN) 已经推进了医疗图像分析,特别是在视网膜动脉/静脉 (A/V) 分类方面.
  • 在管状结构和对视网膜血管细分的有限标记数据方面,CNN面临着挑战.

研究的目的:

  • 提出一个新的半监督点一致性网络 (SPC-Net),以改善视网膜A/V分类.
  • 解决现有的基于CNN的方法在处理微妙的结构变化和数据稀缺方面的局限性.

主要方法:

  • 开发了具有A/V分类 (AVC) 模块和多类点一致性 (MPC) 模块的SPC-Net.
  • AVC模块使用编码器-解码器网络进行监督学习.
  • MPC模块使用点集表示来进行适应性动脉静脉骨分类和点一致性,以减少混.

主要成果:

  • 在监督和半监督的学习环境中,SPC-Net 已经证明了其有效性.
  • 预测地图和点集表示之间的一致性规范化减少了对注释数据的需求.
  • 在公共 (DRIVE,HRF) 和私人 (TR280) 数据集上得到验证,显示出强大的定性和定量结果.
关键词:
动脉/静脉分类的分类方法深度学习是一种深度学习.点的一致性 点的一致性视网膜图像 视网膜图像半监督学习 半监督学习

更多相关视频

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.6K

相关实验视频

Last Updated: Jul 10, 2025

Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

18.8K
Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.6K

结论:

  • 拟议的SPC-Net有效地提高了视网膜A/V分类的准确性.
  • 具有点一致性的半监督学习为数据有限的医学成像任务提供了可行的解决方案.
  • 在不同分辨率的数据集中,SPC-Net的方法是稳定的.