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

Ataxia Telangiectasia Mutated Protein Loss and Benefit From Oxaliplatin-based Chemotherapy in Colorectal Cancer.

Clinical colorectal cancer·2018

Same author

From Checkerboard-Like Sand Barriers to 3D Cu@CNF Composite Current Collectors for High-Performance Batteries.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2018

Same author

[Expression and Regulatory Effect of miR-30b on Dynamin in Cochlear Hair Cells].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2018

Same author

Ratiometric nanothermometer in vivo based on triplet sensitized upconversion.

Nature communications·2018

Same author

CRISPR screens identify genomic ribonucleotides as a source of PARP-trapping lesions.

Nature·2018

Same author

Quantitative Analysis of Sex-Hormone-Binding Globulin Glycosylation in Liver Diseases by Liquid Chromatography-Mass Spectrometry Parallel Reaction Monitoring.

Journal of proteome research·2018

Search research articles

相关实验视频

Updated: Jun 24, 2025

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

核心层次的先前知识受制于多个实例学习对于乳腺组织病理学全幻灯片图像分类.

Xunping Wang¹, Wei Yuan²

¹School of Remote Sensing and Information Engineering, Wuhan University, 129 Luoyu Road, Wuhan 430079, China.

|June 4, 2024

概括

一个新的核心级预先知识受制于多个实例学习 (NPKC-MIL) 模型增强了乳腺癌整片图像分类. 这种方法将深度学习与先前的生物学知识相结合,以提高可解释性和准确性.

关键词:

生物信息学是一种生物信息学.机器学习机器学习

更多相关视频

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

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

Author Spotlight: 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: Jun 24, 2025

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

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

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

Author Spotlight: 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:

在瘤学瘤学.
计算病理学计算病理学
人工智能在医学中的应用

背景情况:

乳腺癌现在是全球最常见的癌症,超过了肺癌.
医学图像分析中的深度学习模型,特别是整个幻灯片图像 (WSIs),缺乏可解释性,阻碍了病理学家的采用.
现有的方法很难将先前的生物学知识整合到深度学习框架中,用于WSI分类.

研究的目的:

为乳房整体幻灯片图像 (WSI) 分类提出一个新的核心级预先知识受制于多个实例学习 (NPKC-MIL) 框架.
提高数字病理学深度学习模型的可解释性和性能.
将手工制作的核心级别功能与基于深度学习的补丁和幻灯片级别功能集成.

主要方法:

利用转移学习用于补丁级特征提取和注意力聚合用于幻灯片级特征聚合.
采用K-近邻 (K-NN) 算法来建立核拓,并为核节点生成手工制作的特征.
结合深度学习功能 (补丁级和幻灯片级) 与手工制作的核心级功能,用于模型微调.

主要成果:

拟议的NPKC-MIL模型在WSI分类中的现有深度学习模型相比,表现优越.
集成核心层次的先前知识显著提高了分类准确性和可解释性.
NPKC-MIL成功地扩大了WSI分类任务的分析维度.

结论:

NPKC-MIL为可解释和准确的乳腺癌WSI分类提供了一个有希望的方法.
将先前的生物知识整合到深度学习模型中,对于推进数字病理学的发展至关重要.
这个框架有可能提高诊断准确性和AI在癌症检测中的临床采用.