Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Biochar-Based Single-Atom Cobalt Catalyst for Efficient Thermal Decomposition of Ammonium Perchlorate: Preparation, Performance and Mechanism.

International journal of molecular sciences·2026

Same author

Hollow NiCo-LDH Nanocage Derived From ZIF-67 as an Efficient Catalyst for the Thermal Decomposition of Ammonium Perchlorate.

Chemistry (Weinheim an der Bergstrasse, Germany)·2026

Same author

Single dose of 5 Gy can damage erythrocytes and consequently induces lymphocyte depletion in spleen and circulating blood.

Frontiers in immunology·2026

Same author

Automated micro-CT quantification of clear aligner fit: a pilot comparison of manufacturing processes.

BMC oral health·2026

Same author

Stability of serum cytokeratin 18-M30 under different storage conditions for drug-induced liver injury assessment.

Pakistan journal of pharmaceutical sciences·2026

Same author

A self-powered photoelectrochemical sensor based on an In<sub>2</sub>O<sub>3</sub>/Ag<sub>2</sub>S heterojunction for tetracycline detection and portable applications.

Mikrochimica acta·2026

Search research articles

相关实验视频

Updated: Jul 12, 2026

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

M4:多代理多门混合专家网络,用于多个实例的学习在他的病理学图像分析.

Junyu Li¹, Ye Zhang², Wen Shu³

¹Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, China.

Medical image analysis

|April 8, 2025

概括

本研究介绍了M4,一种用于分析整个幻灯片图像 (WSIs) 的新型多实例学习框架. M4可以同时预测WSI的多个基因突变,提高效率并捕捉任务间的关系.

关键词:

基因突变是一种基因突变.多任务学习多任务学习多个实例的学习是多个实例的学习.整个幻灯片图像的图像.

更多相关视频

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Published on: April 7, 2023

Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

相关实验视频

Last Updated: Jul 12, 2026

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Published on: April 7, 2023

Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

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) 对于整个幻灯片图像 (WSIs) 在计算病理学中的分析至关重要.
当前的MIL方法往往专注于单个任务,限制效率,忽视任务的相互依赖.

研究的目的:

开发一个高效的MIL框架,同时预测来自WSIs的多个基因突变.
在计算病理学中解决单任务学习的局限性.

主要方法:

提出了一个适应的架构:多门混合专家与多代理多个实例学习 (M4).
实施了多门混合专家策略,用于同时预测多个基因突变.
引入了专家和网关网络的多代理CNN,以捕获WSIs内的补丁互动.

主要成果:

在5个TCGA数据集中,M4显示了显著的改进.
与最先进的单任务MIL方法相比,实现了更高的性能.
成功启用了WSIs多个基因突变的同时预测.

结论:

在WSI分析中,M4框架为多任务学习提供了一种高效和有效的方法.
M4捕捉了任务之间的相关性,优于单一任务的方法.
这项工作通过从WSIs同时预测多个生物标志物来推进计算病理学.