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

Neuroanatomical substrates of perivascular space index: a morphometric and tractography study.

Frontiers in psychiatry·2026
Same author

Neuroendoscopic treatment of a rapidly enlarging choroidal fissure cyst: a case report and literature review.

Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery·2026
Same author

BK channel deficiency promotes lipolysis via an AKT-independent activation of the cAMP/PKA/HSL pathway.

Journal of lipid research·2026
Same author

Multifunctional vanadium-doped carbon dots nanozymes: preparation and applications in colorimetric sensing and tumor therapy.

Mikrochimica acta·2026
Same author

Tailoring vanadium-doped carbon dots as a peroxidase mimic for precise colorimetric sensing of myricetin.

Mikrochimica acta·2026
Same author

Metabotropic signaling downstream of GABA<sub>A</sub> receptors suppresses neuroinflammation in Parkinson's disease.

NPJ Parkinson's disease·2026

相关实验视频

Updated: Feb 18, 2026

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

3.6K

协调泛化和专业化:半监督医疗图像细分的不确定性告知协作学习.

Wenjing Lu, Yi Hong, Yang Yang

    IEEE transactions on medical imaging
    |February 16, 2026
    PubMed
    概括
    此摘要是机器生成的。

    基于不确定性的协作学习 (UnCoL) 通过平衡一般和专业知识来改善半监督的医疗图像细分. 这种方法实现了近乎完全监督的性能,注释要少得多.

    更多相关视频

    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
    06:18

    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

    Published on: April 5, 2024

    1.6K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    835

    相关实验视频

    Last Updated: Feb 18, 2026

    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

    3.6K
    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
    06:18

    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

    Published on: April 5, 2024

    1.6K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    835

    科学领域:

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

    背景情况:

    • 视觉基础模型为医疗图像细分提供了强大的概括性.
    • 这些模型因有限的注释和罕见的病理而难以处理专门的任务,这些病理源于一般先验和特定需求之间的不匹配.

    研究的目的:

    • 引入基于不确定性的协作学习 (UnCoL),这是一个双教师框架,用于半监督的医疗图像细分.
    • UnCoL的目标是协调泛化和专业化,以提高临床任务的性能.

    主要方法:

    • UnCoL采用双教师框架,从结基础模型中提取一般知识,并从适应教师中提取特定任务的知识.
    • 伪标签学习是通过预测不确定性来适应调节的,以稳定模两可的区域中的学习,并抑制不可靠的监督.

    主要成果:

    • 在各种2D和3D医疗图像细分基准中,UnCoL的表现始终优于现有的半监督方法.
    • 该模型实现了近乎完全监督的性能,显示了显著减少的注释要求.

    结论:

    • 基于不确定性的协作学习有效地弥合了在医学图像细分方面的一般预培训和专业临床要求之间的差距.
    • UnCoL提供了一个有前途的解决方案,用于高效和准确的医疗图像细分,使用有限的标记数据.