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

Boundary-aware and discrepancy-guided dynamic pseudo-labeling with consistency learning for semi-supervised 3D TOF-MRA cerebrovascular segmentation.

Physics in medicine and biology·2026
Same author

Anisotropic Black Phosphorus Synaptic Device for Neuromorphic Applications.

Advanced materials (Deerfield Beach, Fla.)·2016
Same author

An accurate clone-based haplotyping method by overlapping pool sequencing.

Nucleic acids research·2016
Same author

Upregulation of proangiogenic factors expression in the synovium of temporomandibular joint condylar hyperplasia.

Oral surgery, oral medicine, oral pathology and oral radiology·2016
Same author

Synthesis and Applications of π-Extended Naphthalene Diimides.

Chemical record (New York, N.Y.)·2016
Same author

Observation of the Singly Cabibbo-Suppressed Decay D^{+}→ωπ^{+} and Evidence for D^{0}→ωπ^{0}.

Physical review letters·2016

相关实验视频

Updated: Jul 6, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

协作学习,以实现注释效率高的体积测量MR图像细分.

Yousuf Babiker M Osman1,2, Cheng Li1, Weijian Huang1,2,3

  • 1Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.

Journal of magnetic resonance imaging : JMRI
|December 29, 2023
PubMed
概括

这项研究引入了一种新的深度学习方法,用于仅使用单个2D切片标签对3DMRI图像进行细分. 这种方法显著提高了前列腺和左心室的细分精度,减少了大量手动注释的需要.

关键词:
伪标签是一种伪标签.自主监督学习学习半监督学习 半监督学习有稀少的注释.大量的MR图像细分.

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K

相关实验视频

Last Updated: Jul 6, 2025

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 深度学习在MR图像细分方面表现出色,具有足够的标记数据.
  • 手动注释3DMRI图像是劳动密集型的,需要专家知识.

研究的目的:

  • 开发一种使用稀疏注释的深度学习方法,特别是每个3D训练MR图像单一的2D切片标签.
  • 为了应对3D医学图像细分中的有限注释数据的挑战.

主要方法:

  • 一项回顾性研究,涉及来自两个公共数据集的150名受试者 (前列腺和左心房细分).
  • 一种集成半监督和自我监督学习的协作学习方法,在标记的中央和未标记的非中央切片上进行训练.
  • 使用B-IoU,Dice系数,表面距离和体积差异进行定量评估,并对 t 测试进行统计学意义测试.

主要成果:

  • 与完全监督和其他半监督方法相比,拟议的方法显著提高了细分精度.
  • 平均B-IoU在前列腺细分方面增加了超过10.0% (70.3%±7.6%),在左心室细分方面增加了超过6.0% (66.1%±6.8%).
  • 该方法在插值一致性培训 (ICT) 和其他比较技术中表现出优异的性能.

结论:

  • 一种协作式学习方法有效地使用稀疏的注释对前列腺和左前庭进行细分.
  • 开发的方法提供了一个高度准确的解决方案,用于3DMR图像细分,标签的努力最小.