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

Nonparametric change-point control charts for joint monitoring of mean and covariance with application to medical imaging data.

Statistical methods in medical research·2026
Same author

Development and validation of an event-specific detection method for WYN029GmA soybean based on TaqMan qPCR.

Frontiers in plant science·2026
Same author

Prognostic Value of Coronary Sinus Flow and Aortic Pressure Gradient Quantified by 4D Flow CMR in AMI.

Academic radiology·2026
Same author

Isolation, identification and pathogenicity analysis of a virulent duck enteritis virus strain causing outbreak in vaccinated duck flocks.

Poultry science·2026
Same author

DiRIC: Diffusion Prior Refinement for Efficient Low-rate Image Compression.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Research on polygonal microcavity 9 μm quantum cascade lasers with waveguide output from a master oscillator power amplifier.

Optics express·2026

相关实验视频

Updated: Jul 26, 2025

Author Spotlight: A Model to Study the Systemic and Local Dynamics of CD8+ T Cells During LN Metastasis
07:45

Author Spotlight: A Model to Study the Systemic and Local Dynamics of CD8+ T Cells During LN Metastasis

Published on: January 26, 2024

2.0K

dMIL-Transformer:通过整合淋巴结转移分类的形态和空间信息进行多实例学习.

Yang Chen, Zhuchen Shao, Hao Bian

    IEEE journal of biomedical and health informatics
    |June 13, 2023
    PubMed
    概括
    此摘要是机器生成的。

    这项研究引入了一种新的dMIL-Transformer框架,用于自动化淋巴结转移 (LNM) 分类. 该方法有效地整合了形态和空间数据,大大提高了LNM检测的诊断准确性.

    更多相关视频

    Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma
    07:52

    Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma

    Published on: January 9, 2019

    19.8K
    A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis
    07:41

    A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

    Published on: March 8, 2022

    2.5K

    相关实验视频

    Last Updated: Jul 26, 2025

    Author Spotlight: A Model to Study the Systemic and Local Dynamics of CD8+ T Cells During LN Metastasis
    07:45

    Author Spotlight: A Model to Study the Systemic and Local Dynamics of CD8+ T Cells During LN Metastasis

    Published on: January 26, 2024

    2.0K
    Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma
    07:52

    Multiplexed Fluorescent Immunohistochemical Staining, Imaging, and Analysis in Histological Samples of Lymphoma

    Published on: January 9, 2019

    19.8K
    A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis
    07:41

    A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

    Published on: March 8, 2022

    2.5K

    科学领域:

    • 计算病理学计算病理学
    • 医疗图像分析 医疗图像分析
    • 癌症诊断 癌症诊断 癌症诊断

    背景情况:

    • 淋巴结转移的自动分类对于癌症诊断和预后至关重要.
    • 准确的LNM分类需要整合瘤形态和空间分布,这对现有的方法来说是具有挑战性的.

    研究的目的:

    • 为改进LNM分类提出一个新的两级dMIL-Transformer框架.
    • 通过多重实例学习 (MIL) 有效地整合瘤区域的形态和空间信息.

    主要方法:

    • 开发了一种双重的Max-Min MIL (dMIL) 策略,从组织病理学图像中选择关键的阳性实例.
    • 一个基于变压器的MIL聚合器被设计成使用自我注意机制集成实例级信息.
    • 该框架学习袋级表示,以预测具有增强可解释性的LNM类别.

    主要成果:

    • 该dMIL策略建立了一个较高的决策边界,例如选择.
    • 在三个LNM数据集中,dMIL-Transformer框架实现了1.79%-7.50%的性能改进,相比于最先进的方法.
    • 拟议的方法证明了复杂的LNM分类任务的有效处理,具有强大的可视化能力.

    结论:

    • dMIL-Transformer框架为自动化的LNM分类提供了一个强大的和可解释的解决方案.
    • 通过两阶段的MIL方法整合形态和空间特征可以显著提高分类性能.
    • 这一框架有望在癌症诊断中推进计算病理学.