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

A multimodal vision-language model for generalizable annotation-free pathology localization.

Nature biomedical engineering·2026
Same author

Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation.

Research (Washington, D.C.)·2025
Same author

Cross-sequence semi-supervised learning for multi-parametric MRI-based visual pathway delineation.

Physics in medicine and biology·2025
Same author

Mammo-AGE: deep learning estimation of breast age from mammograms.

Nature communications·2025
Same author

SamRobNODDI:<i>q</i>-space sampling-augmented continuous representation learning for robust and generalized NODDI.

Physics in medicine and biology·2025

相关实验视频

Updated: Jul 9, 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

稀有注释学习用于密集体积MR图像细分与不确定性估计.

Yousuf Babiker M Osman1,2, Cheng Li1,3, Weijian Huang1,2,4

  • 1Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, People's Republic of China.

Physics in medicine and biology
|November 30, 2023
PubMed
概括

这项研究介绍了ESA-Net,这是一个用于3D医疗图像细分的新型神经网络,它以最小的注释表现出色. 它有效地利用未标记的数据来提高细分精度,即使只有一个中央切片标签.

关键词:
有稀少的注释.不确定性估计估计的不确定性大量的MR图像细分.

更多相关视频

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

9.9K
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

相关实验视频

Last Updated: Jul 9, 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
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

9.9K
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

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:

  • 训练神经网络用于医疗图像细分需要大量,准确的注释数据.
  • 获取如此详细的注释是劳动密集型,耗时,需要专家知识.
  • 这种注释数据的稀缺性在医学成像领域提出了重大挑战.

研究的目的:

  • 开发一个神经网络框架,能够使用极其有限的注释数据进行3D体积细分.
  • 为应对医疗图像细分方面的培训样本不足的挑战.
  • 探索在细分过程中有效利用未标记数据的方法.

主要方法:

  • 为3D细分提出了极为稀疏的注释神经网络 (ESA-Net) 框架.
  • 开发了一个由四个组件组成的架构,包括切片内部像素依赖性,切片间相关性,伪标签融合和网络优化模块.
  • 使用不确定性估计,时间组合,自我监督注册和轮换组合用于标签生成和传播.

主要成果:

  • 在具有挑战性的磁共振图像分割任务中,ESA-Net表现出卓越的细分性能.
  • 与五种最先进的方法相比,该框架在非常稀疏的注释条件下始终取得了更好的结果.
  • 验证了利用未标记数据信息的有效性,以改善细分.

结论:

  • 欧洲航天局网络 (ESA-Net) 提供了一种有效的解决方案,用于以最小的注释进行3D医疗图像细分.
  • 拟议的方法成功地利用从未标记的数据中获取的切片内和切片间信息.
  • 突出了不确定性估计和新型伪标签策略在数据稀缺细分场景中的潜力.