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

Prevalence of Vitamin D Deficiency in a Large Newborn Cohort from Northern United States and Effect of Intrauterine Drug Exposure.

Nutrients·2020
Same author

DNA Methylation and Bladder Cancer: Where Genotype does not Predict Phenotype.

Current genomics·2020
Same author

Diagnostic performance of EUS in non-jaundiced patients with an incidental finding of double duct sign on cross-sectional imaging: A systematic review and meta-analysis.

Pancreatology : official journal of the International Association of Pancreatology (IAP) ... [et al.]·2020
Same author

Giant Liver Hemangiomas: A Plea for Early Surgical Referral and Resection.

Case reports in surgery·2020
Same author

DeconPeaker, a Deconvolution Model to Identify Cell Types Based on Chromatin Accessibility in ATAC-Seq Data of Mixture Samples.

Frontiers in genetics·2020
Same author

The lurking scourge of multidrug resistant Candida auris in times of COVID-19 pandemic.

Journal of global antimicrobial resistance·2020

相关实验视频

Updated: Jan 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

使用深度学习对比HER2评分的低分辨率和高分辨率特征.

Ekansh Chauhan1, Anila Sharma2, Amit Sharma1

  • 1Centre for Visual Information Technology, International Institute of Information Technology, Hyderabad 500032, Telangana, India.

Journal of pathology informatics
|December 25, 2025
PubMed
概括

这项研究使用IHC图像上的深度学习自动化HER2乳腺癌分类. 一个端到端的ConvNeXt模型实现了83.52%的F1得分,提高了准确性和可重复性,以获得更好的患者结果.

关键词:
深度学习是一种深度学习.数字病理学数字病理学低HER2的乳腺癌.免疫组织化学 免疫组织化学

更多相关视频

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
11:34

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

Published on: December 5, 2017

13.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

相关实验视频

Last Updated: Jan 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K
Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
11:34

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

Published on: December 5, 2017

13.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

科学领域:

  • 在瘤学瘤学.
  • 计算病理学计算病理学
  • 生物标记分析 生物标记分析

背景情况:

  • 在乳腺癌中,准确的HER2 (人类表皮生长因子受体2) 分类对于向治疗选择至关重要.
  • 传统的免疫组织化学 (IHC) 分类是主观的,并且受到观察者之间的变化影响.
  • 三种分类 (0,低,高) 对于识别可能从HER2向治疗中受益的患者至关重要.

研究的目的:

  • 开发和评估深度学习模型,以使用IHC图像进行自动化3向HER2分类.
  • 引入印度病理学乳腺癌数据集,用于研究自动化乳腺癌诊断.
  • 将端到端深度学习模型的性能与传统基于补丁的方法进行比较.

主要方法:

  • 印度病理学乳腺癌数据集与500名患者的HER2 IHC幻灯片的开发.
  • 培训和评估各种深度学习模型,包括一个端到端的ConvNeXt网络.
  • 用ConvNeXt模型的低分辨率IHC图像来评估分类性能.

主要成果:

  • 端到端的ConvNeXt网络在三向HER2分类方面获得了83.52%的F1总分.
  • 这比基于补丁的方法改进了5.35%.
  • 各类F1分数为75.6% (HER2-0),82.4% (HER2-low) 和91.5% (HER2-high),在区分HER2-0和HER2-low方面存在挑战.

结论:

  • 深度学习技术,特别是端到端的ConvNeXt模型,显示出在乳腺癌中准确和可重复的HER2分类的巨大潜力.
  • 自动化HER2分类可以减少病理学家的工作量和观察者之间的变化.
  • 将这些人工智能工具集成到临床工作流程中,可以通过优化向治疗选择来提高患者的治疗结果.