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

Predicting mortality risk in pediatric severe pneumonia using a CNN-BiLSTM model with dynamic clinical indicators.

Respiratory medicine·2026

Same author

Sex differences in cognitive function trajectories and influencing factors in older adults: A machine learning study based on CHARLS and HRS.

Journal of affective disorders·2026

Same author

Can health poverty alleviation policies simultaneously mitigate current and future medical-related poverty? Evidence from four waves (2011-2018) of the China health and retirement longitudinal study (CHARLS).

Archives of public health = Archives belges de sante publique·2025

Same author

Genomic and genetic insights into speciation and pigment pattern diversification in <i>Danio</i> fishes.

bioRxiv : the preprint server for biology·2025

Same author

Predicting MammaPrint Recurrence Risk from Breast Cancer Pathological Images Using a Weakly Supervised Transformer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Same author

A machine learning-based method to optimize the immunogenicity of human leukocyte antigen class I-restricted neoantigens.

Briefings in bioinformatics·2025

Search research articles

相关实验视频

Updated: Jun 22, 2025

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Published on: December 5, 2017

PhiHER2:基于表型的弱监督模型,用于从病理图像中预测HER2状态.

Chaoyang Yan^1,2, Jialiang Sun^1,2, Yiming Guan^1,2

¹College of Computer Science, Nankai University, Tianjin 300071, China.

Bioinformatics (Oxford, England)

|June 28, 2024

概括

我们开发了 PhiHER2,这是一种新的计算方法,用于预测乳腺癌中人类表皮生长因子受体2 (HER2) 状态,使用病理图像. 这种方法有效地利用瘤异质性来准确预测HER2状态.

更多相关视频

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

相关实验视频

Last Updated: Jun 22, 2025

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Published on: December 5, 2017

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Optimization of a Multiplex RNA-based Expression Assay Using Breast Cancer Archival Material

Published on: August 1, 2018

科学领域:

计算病理学计算病理学
生物医学成像分析分析
机器学习用于癌症诊断和癌症诊断

背景情况:

准确的人类表皮生长因子受体2 (HER2) 状态识别对于乳腺癌 (BC) 预后和治疗至关重要.
病理幻灯片是黄金标准,但分析具有内异质性的高分辨率图像是具有挑战性的.
计算分析为发现与HER2状态相关的形态模式提供了潜力.

研究的目的:

开发一种基于表型的,低监督的多个实例学习架构 (PhiHER2) 来精确地从BC病理图像中预测HER2状态.
为了提高预测准确性,利用内形态的形态异质性.
为与HER2状态相关的形态模式提供可解释的见解.

主要方法:

开发了一个层次化的原型集群模块,以识别整个幻灯片图像 (WSI) 中的代表性表型.
集成的表型嵌入到交叉关注模块中,以增强特征交互和聚合.
采用基于表型的特征空间来捕获和利用形态异质性用于HER2预测.

主要成果:

通过表型指导,PhiHER2表现出卓越的WSI级别代表性.
该模型在现实世界乳腺癌数据集上显著优于现有方法.
解释性分析提供了关于形态表型和HER2状态之间的关系的明确见解.

结论:

PhiHER2为乳腺癌中HER2状态预测提供了强大而准确的计算方法.
基于表型的策略有效地解决了病理图像中内异质性的挑战.
该模型的可解释性增强了对HER2状态形态驱动因素的临床理解.