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 relationship between the pore architecture of MFI zeolites and isoamylene oligomerization.

Physical chemistry chemical physics : PCCP·2026
Same author

TRA2A negatively regulates HIV-1-induced macrophage pyroptosis by mediating TXNIP expression in an m6A-dependent manner.

Cell death discovery·2026
Same author

Global current systems in the magnetosphere of Mercury.

Nature communications·2026
Same author

Effects of Clostridium butyricum on the growth performance, digestion, immunity, and gut microbiota of Rana catesbiana.

Journal of applied microbiology·2026
Same author

Tisotumab vedotin versus chemotherapy in Chinese patients with recurrent or metastatic cervical cancer with disease progression on or after systemic therapy.

Chinese medical journal·2026
Same author

Mars' induced magnetosphere can form under radial interplanetary magnetic field.

Innovation (Cambridge (Mass.))·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026
Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026
查看所有相关文章

相关实验视频

Updated: May 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

325

整张幻灯片图像多个实例学习的松散伪袋增强.

Jiuyang Dong, Junjun Jiang, Kui Jiang

    IEEE transactions on medical imaging
    |May 14, 2025
    PubMed
    概括
    此摘要是机器生成的。

    DPBAug通过生成高质量的伪袋来增强整个幻灯片图像 (WSI) 分类的多个实例学习 (MIL). 这种新的方法提高了分类性能和数据效率,有助于临床应用.

    更多相关视频

    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

    2.6K
    Serial Two-Photon Tomography of the Whole Marmoset Brain for Neuroanatomical Analyses
    04:02

    Serial Two-Photon Tomography of the Whole Marmoset Brain for Neuroanatomical Analyses

    Published on: January 17, 2025

    340

    相关实验视频

    Last Updated: May 16, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    325
    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

    2.6K
    Serial Two-Photon Tomography of the Whole Marmoset Brain for Neuroanatomical Analyses
    04:02

    Serial Two-Photon Tomography of the Whole Marmoset Brain for Neuroanatomical Analyses

    Published on: January 17, 2025

    340

    科学领域:

    • 计算病理学计算病理学
    • 医学中的人工智能.
    • 数字病理学数字病理学

    背景情况:

    • 多个实例学习 (MIL) 是整个幻灯片图像 (WSI) 分类的标准.
    • 现有的MIL方法面临的挑战是由于有限的标记WSIs和杂的伪袋增强.
    • 改进数据增强对于提高数字病理学的MIL性能至关重要.

    研究的目的:

    • 介绍DPBAug,一个新的伪袋生成范式用于WSI数据增强.
    • 解决当前MIL增强方法中噪音高的伪标签和低质量的伪袋的局限性.
    • 提高WSI分析的MIL方法的分类性能,可靠性和数据效率.

    主要方法:

    • DPBAug采用了一个幻灯片内部伪袋生成模块,具有表型分区和实例采样与替换.
    • 一个间幻灯片伪袋融合模块集成信息跨多个WSIs高质量的样本生成.
    • 伪袋内存更新模块优先考虑有价值的合成伪袋以提高网络性能.

    主要成果:

    • 在各种公共WSI数据集上,DPBAug显著优于现有的增强方法.
    • 拟议的方法提高了多个MIL基线的分类性能和可靠性.
    • 对于MIL方法,DPBAug显示了改善的概括性和数据效率.

    结论:

    • DPBAug提供了一个强大的解决方案,用于WSI数据增强MIL.
    • 该方法有助于在临床实践和罕见癌症研究中采用MIL.
    • 通过提高WSI分类能力,DPBAug推进了计算病理学领域的发展.