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

Comprehensive multicriteria life cycle assessment of biopsy processing in a surgical pathology department.

American journal of clinical pathology·2026
Same author

What is the carbon footprint of a 100% digital pathology scenario in France?

Pathology·2026
Same author

MIPHEI-ViT: Multiplex immunofluorescence prediction from H&E images using ViT foundation models.

Computers in biology and medicine·2026
Same author

Exploring the risks of over-reliance on AI in diagnostic pathology. What lessons can be learned to support the training of young pathologists?

PloS one·2025
Same author

Innate immunity and the NF-κB pathway control prostate stem cell plasticity, reprogramming and tumor initiation.

Nature cancer·2025
Same author

First Case of Ovarian Metastases From a Primary Retroperitoneal Mucinous Carcinoma Associated With Teratoma, With KRAS and ERBB3 Mutations: Case Report and Literature Review.

International journal of gynecological pathology : official journal of the International Society of Gynecological Pathologists·2025

相关实验视频

Updated: Jul 25, 2025

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

12.7K

通过通过弱监督,受约束的深度学习方法评估临床指南来解释HER2评分.

Manh-Dan Pham1, Guillaume Balezo1, Cyprien Tilmant2

  • 1Tribun Health, 2 Rue du Capitaine Scott, 75015 Paris, France.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
|June 25, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种半自动深度学习方法,以改善乳腺癌中人类表皮生长因子受体-2 (HER2) 评分,减少病理学家的变异性. 人工智能模型获得了0.78的F1得分,提高了诊断准确性和可解释性.

关键词:
乳腺癌是什么? 乳腺癌是什么深度学习 (Deep Learning) 是一种深度学习.数字病理学数字病理学在HER2评分中,HER2的分数是:弱监督的受约束优化受约束优化

更多相关视频

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.1K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

635

相关实验视频

Last Updated: Jul 25, 2025

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

12.7K
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.1K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

635

科学领域:

  • 数字病理学数字病理学
  • 人工智能在医学中的应用
  • 瘤学生物标志物

背景情况:

  • 准确的人体表皮生长因子受体-2 (HER2) 表达的评估对于乳腺癌的治疗选择至关重要.
  • 由于染色不一致和视觉估计挑战,HER2评分表现出高的观察者间变异性.
  • 现有的方法对于病理学家来说缺乏解释性,阻碍了临床采用.

研究的目的:

  • 为 HER2 评分开发一种半自动,可解释的深度学习方法.
  • 将人工智能驱动的HER2分类与美国临床瘤学会/美国病理学家学院 (ASCO/CAP) 的指南保持一致.
  • 为了减少在HER2评估中观察者之间的变异性.

主要方法:

  • 开发了一种两阶段的深度学习模型:在一个感兴趣的区域 (ROI) 中进行瘤细分,然后进行HER2类别分类.
  • 使用弱监督,受约束的优化进行分类,确保瘤表面百分比遵守指南.
  • 采用了多病理学家的共识标签策略和监督模型输出的改进.

主要成果:

  • 该模型在测试组件上获得了0.78的F1得分.
  • 深度学习方法证明了病理学家的解释性,提供HER2类百分比.
  • 该系统有助于评估可疑的情况下,病理学家达不到共识.

结论:

  • 拟议的半自动深度学习方法为乳腺癌中的HER2评分提供了可解释和准确的解决方案.
  • 这种方法有可能使HER2评估标准化并改善治疗选择.
  • 这项研究有助于在数字病理学中开发可解释的AI模型.