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

Apigenin restricts FMDV infection and inhibits viral IRES driven translational activity.

Viruses·2015
Same author

Diffraction in a stratified region of a high numerical aperture Fresnel zone plate: a simple and rigorous integral representation.

Optics express·2015
Same author

Comparative Genetics of Seed Size Traits in Divergent Cereal Lineages Represented by Sorghum (Panicoidae) and Rice (Oryzoidae).

G3 (Bethesda, Md.)·2015
Same author

[Recent Researches on Optical in vivo Imaging: a review].

Zhongguo Zhong xi yi jie he za zhi Zhongguo Zhongxiyi jiehe zazhi = Chinese journal of integrated traditional and Western medicine·2015
Same author

[An analysis of relevant factors influencing the prognosis of post cardiac arrest syndrome].

Zhonghua wei zhong bing ji jiu yi xue·2015
Same author

Transparent ALD-grown Ta2O5 protective layer for highly stable ZnO photoelectrode in solar water splitting.

Chemical communications (Cambridge, England)·2015

相关实验视频

Updated: Jul 5, 2025

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
09:03

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

Published on: April 13, 2019

8.2K

BoNuS:用部分点标签进行核细分的边界采矿.

Yi Lin, Zeyu Wang, Dong Zhang

    IEEE transactions on medical imaging
    |January 17, 2024
    PubMed
    概括

    本研究介绍了BoNuS,一种使用部分点标签的弱监督核细分方法. 它通过准确识别核内部和边界,显著减少了数字病理学的手动注释工作.

    科学领域:

    • 数字病理学数字病理学
    • 计算机视觉 计算机视觉
    • 生物医学图像分析

    背景情况:

    • 精确的细胞核细分对于数字病理学的定量分析至关重要.
    • 手动注释核是劳动密集型,耗时,需要专业知识.
    • 需要自动化方法来克服手动注释的局限性.

    研究的目的:

    • 开发一种弱监督的核细分方法,只需要部分点标签.
    • 引入一种新的边界挖掘框架 (BoNuS),用于同时学习核内部和边界信息.
    • 通过将核子检测模块纳入课程学习来应对部分点标签的挑战.

    主要方法:

    • 一个新的边界挖掘损失函数在多个实例的学习框架中使用对对像素亲和力指导模型.
    • 建议使用课程学习的核检测模块来处理缺失的核信息.
    • BoNuS框架同时从有限的点注释中学习核内部和边界特征.

    主要成果:

    • 拟议的BoNuS方法与现有的弱监督核细分技术相比,显示出更高的性能.
    • 在MoNuSeg,CPM和CoNIC数据集上的验证证实了该方法的有效性.
    • 这种方法成功地使用显著更少的注释力来分割核.

    更多相关视频

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.4K
    Using Computer Vision Libraries to Streamline Nuclei Quantification
    06:25

    Using Computer Vision Libraries to Streamline Nuclei Quantification

    Published on: June 6, 2025

    174

    相关实验视频

    Last Updated: Jul 5, 2025

    Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
    09:03

    Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

    Published on: April 13, 2019

    8.2K
    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
    10:39

    A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

    Published on: May 24, 2022

    2.4K
    Using Computer Vision Libraries to Streamline Nuclei Quantification
    06:25

    Using Computer Vision Libraries to Streamline Nuclei Quantification

    Published on: June 6, 2025

    174

    结论:

    • 使用部分点标签的弱监督核细分是可行的和有效的.
    • 博努斯框架为数字病理学中高效准确的核细分提供了一个有前途的解决方案.
    • 这种方法减少了对广泛的手动注释的依赖,加速了病态图像分析.