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

Structural-functional network decoupling in early stage amyotrophic lateral sclerosis reveals cell-type specific transcriptional signatures.

BMC medicine·2026
Same author

Metal-phenolic nanocapsules enable a self-amplifying cuproptosis-STING cascade for synergistic cancer immunotherapy.

Bioactive materials·2026
Same author

Corrigendum to "Reduced skeletal muscle index during follow-up as a mortality risk factor in maintenance hemodialysis patients with end-stage renal disease". [Eur. J. Radiol. 200 (2026) 112857].

European journal of radiology·2026
Same author

Quantitative susceptibility mapping reveals widespread brain iron abnormalities in sporadic patients with early-stage amyotrophic lateral sclerosis.

Brain communications·2026
Same author

Progressive choroid plexus enlargement across disease stages in patients with sporadic amyotrophic lateral sclerosis.

Neurobiology of disease·2026
Same author

Deep learning reconstruction improves detection of focal liver lesions in hepatobiliary phase compared to conventional EOB-MRI.

Frontiers in medicine·2026

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

半监督医疗图像分割使用交叉风格一致性与形状意识和局部上下文约束.

Jinhua Liu, Christian Desrosiers, Dexin Yu

    IEEE transactions on medical imaging
    |November 30, 2023
    PubMed
    概括
    此摘要是机器生成的。

    这项研究引入了一种新的半监督深度学习框架,用于医疗图像细分,以有限的标记数据提高解剖学准确性. 该方法通过利用形状信息和不确定性估计来提高细分性能.

    更多相关视频

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    406
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.6K

    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
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    406
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.6K

    科学领域:

    • 医疗图像分析 医学图像分析
    • 深度学习是一种深度学习.
    • 计算机视觉 计算机视觉 计算机视觉

    背景情况:

    • 半监督深度学习方法在医疗图像细分方面面临挑战,因为标记数据不足.
    • 数据有限阻碍了捕捉解剖学复杂性和变异性,影响了临床应用.

    研究的目的:

    • 开发一种新的半监督细分框架,用于解剖学上可信的医学图像预测.
    • 有效地利用未标记的数据来提高细分精度.

    主要方法:

    • 一个具有两个平行网络的框架:形状无意识和形状意识,使相互学习成为可能.
    • 形状感知网络引入隐式形状指导;形状不可知网络使用伪标签的不确定性估计.
    • 跨式一致性策略丰富数据,防止过度匹配;新的损失术语增强了当地环境的学习.

    主要成果:

    • 拟议的方法在三个医学图像数据集上优于现有的半监督细分技术.
    • 与其他方法相比,该框架在形状感知方面表现优越.
    • 即使使用有限的标记数据,也可以实现解剖学上可信的预测.

    结论:

    • 开发的半监督框架有效地解决了医疗图像细分中的数据稀缺问题.
    • 形状意识,不确定性估计和交叉风格一致性的组合显著提高了细分精度和形状忠实度.
    • 这种方法为现实世界的临床应用提供了一个有希望的解决方案,需要精确的解剖细分.