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

Artificial intelligence-detected HER2 strong-positive tumor proportion predicts FISH positivity and treatment response in breast cancer.

PloS one·2026
Same author

Tumor Spread through Air Spaces in Early-Stage Lung Adenocarcinoma: Surgical Implications and Patient Management Strategies.

Journal of chest surgery·2026
Same author

Longitudinal multi-platform profiling reveals temporal dynamics of HER2, TROP2, PD-L1 and tumor-infiltrating lymphocytes in triple-negative breast cancer.

medRxiv : the preprint server for health sciences·2026
Same author

A foundation model of cancer genotype enables precise predictions of therapeutic response.

Cancer discovery·2026
Same author

Imaging of Small Cell Lung Cancer: An Updated Overview of Current and Emerging Applications.

Radiology. Imaging cancer·2026
Same author

Clinical and Molecular Characterization of a Rare EGFR cis Compound L833V/H835L Mutation in Non-Small Cell Lung Cancer.

Cancer research communications·2026

相关实验视频

Updated: Jan 11, 2026

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

深度学习从组织学图像中预测EGFR突变状态 在非小细胞肺癌中.

Jongchan Park1, Sangwon Shin1, Woochan Hwang1

  • 1Lunit, Seoul, Republic of Korea.

Cancer research communications
|November 10, 2025
PubMed
概括

深度学习模型现在可以使用标准组织学图像预测非小细胞肺癌 (NSCLC) 的EGFR突变. 这种人工智能工具显示出高精度,可能会提高全球生物标志物测试率.

更多相关视频

Author Spotlight: Advancements in Molecular Biomarker Testing for Non-Squamous Non-Small Cell Lung Cancer
07:59

Author Spotlight: Advancements in Molecular Biomarker Testing for Non-Squamous Non-Small Cell Lung Cancer

Published on: September 8, 2023

1.6K
A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
13:34

A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds

Published on: April 6, 2016

10.6K

相关实验视频

Last Updated: Jan 11, 2026

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
Author Spotlight: Advancements in Molecular Biomarker Testing for Non-Squamous Non-Small Cell Lung Cancer
07:59

Author Spotlight: Advancements in Molecular Biomarker Testing for Non-Squamous Non-Small Cell Lung Cancer

Published on: September 8, 2023

1.6K
A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
13:34

A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds

Published on: April 6, 2016

10.6K

科学领域:

  • 数字病理学数字病理学
  • 在瘤学中使用人工智能
  • 生物标志物发现发现

背景情况:

  • 非小细胞肺癌 (NSCLC) 的EGFR突变查具有全球变异性,造成了显著的护理差距.
  • 深度学习 (DL) 显示出从组织学图像中提取可操作特征的前景,在其他领域获得监管批准.
  • 整合预测DL可以提高NSCLC的EGFR突变查率.

研究的目的:

  • 开发和验证一个DL模型,用于从NSCLC中常规的血素和素 (H&E) 染色组织学图像中预测EGFR突变状态.
  • 评估模型在各种数据集中的性能,包括各种组织学亚型,样本类型和成像平台.

主要方法:

  • 一个DL模型,Lunit SCOPE基因型预测器,在超过12,000张全幻灯片图像上接受了训练.
  • 该模型在不同的数据集 (n=1,461和n=599) 和多扫描仪测试集 (n=2,261) 上进行了验证.
  • 在不同的子组中,使用接收器操作特征曲线 (AUROC) 下的面积来评估性能.

主要成果:

  • 在初始验证组中,DL模型实现了0.905的整体AUROC.
  • 在样本类型 (活检:0.804,切除:0.912) 和组织学亚型 (腺癌:0.880) 中观察到强大的性能.
  • 该模型在独立的国际测试组中获得了0.860的AUROC,并在多个幻灯片扫描仪中显示出高一致性.

结论:

  • 卢尼特SCOPE基因型预测器有效地从NSCLC的常规组织学图像中预测EGFR突变状态.
  • 该模型在各种环境中的验证性能支持其在常规临床实践中的潜在应用.
  • 这种人工智能驱动的方法可能有助于增强分子EGFR突变查,并提高生物标志物测试率.