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

The Role of Hemoglobin in Temporomandibular Joint Osteoarthritis and the Therapeutic Potential of Hydroxyurea.

International journal of dentistry·2026
Same author

Relationship between severe tooth wear and temporomandibular disorders: a cross-sectional study using propensity score matching analysis.

BMC oral health·2026
Same author

Segment anything small for ultrasound: Enhancing segmentation with non-generative augmentation.

PLOS digital health·2026
Same author

Correction: Photobiomodulation mitigates blood-brain barrier disruption in APP/PS1 mouse model of Alzheimer's disease by activating the AMPK pathway.

Alzheimer's research & therapy·2026
Same author

Molecular heterogeneity of the non-human primate cochlea.

Nature communications·2026
Same author

Correction: Photobiomodulation modulates mitochondrial energy metabolism and ameliorates neurological damage in an APP/PS1 mouse model of Alzheimer's disease.

Alzheimer's research & therapy·2026

相关实验视频

Updated: Jul 12, 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

对3D医疗图像数据进行光混合监督细分.

Hongxu Yang1, Tao Tan1, Pal Tegzes2

  • 1GE Healthcare, Eindhoven, The Netherlands.

Medical physics
|November 1, 2023
PubMed
概括
此摘要是机器生成的。

本研究引入了用于3D医疗图像细分的混合监督学习方法,大大减少了注释工作. 这种方法实现了稳定和准确的细分,即使在宽松的界限框注释中,也超过了最先进的方法.

关键词:
3D医疗图像 3D医学图像相反的学习学习学习.混合监督学习学习.放松的界限框框可以放松.

更多相关视频

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.1K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

相关实验视频

Last Updated: Jul 12, 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
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.1K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 准确的3D语义细分对于临床应用至关重要.
  • 对于3D医疗数据的voxel级注释是劳动密集型的,并引发了隐私问题.
  • 目前的切片对切片注释方法耗时.

研究的目的:

  • 开发一个3D细分模型,减少注释的努力.
  • 克服现有的弱监督方法的局限性,需要严格的界限框.
  • 为了使稳定的模型训练使用放松的界限框注释.

主要方法:

  • 为3D细分提出了一种混合监督的培训策略.
  • 只有一个切片需要完整的轮注释;其他人使用放松的边界框.
  • 该方法整合了完全监督的学习,放松的边界框先验和对比的学习.

主要成果:

  • 实现了高细分的子得分:在前列腺MRI上达到85.3%,在静脉瘤数据集上达到83.3%.
  • 使用宽松的界限框注释,超越了最先进的方法.
  • 尽管边界框准确度的变化,但证明了稳定的模型性能.

结论:

  • 介绍了一种用于3D医学成像的混合监督学习方法.
  • 该方法允许稳定的细分与减少注释准确性要求.
  • 便于在大型医疗数据集上更容易地训练模型.