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

Consumption of whole and refined grains and the risk of gastric cancer: a pooled analysis within the Stomach cancer Pooling (StoP) Project.

European journal of nutrition·2026
Same author

Artificial intelligence for predicting transient hypocalcemia after total thyroidectomy.

Scientific reports·2026
Same author

MRI response to neoadjuvant chemotherapy and prognostic implications in breast cancer patients.

The British journal of radiology·2026
Same author

Endoscopic liquid biopsies of gastric fluid in a large human patient cohort reveal DNA content as a candidate tumor biomarker in gastric cancer.

eLife·2025
Same author

Somatic hypermutation patterns are shaped by both motif position and sequence grammar.

The EMBO journal·2025
Same author

Overall survival of patients with second primary breast cancer associated with molecular subtype and epidemiological profile at a cancer center.

Breast cancer (Tokyo, Japan)·2025

相关实验视频

Updated: Jun 16, 2025

Protocol for HER2 FISH Using a Non-cross-linking, Formalin-free Tissue Fixative to Combine Advantages of Cryo-preservation and Formalin Fixation
10:21

Protocol for HER2 FISH Using a Non-cross-linking, Formalin-free Tissue Fixative to Combine Advantages of Cryo-preservation and Formalin Fixation

Published on: December 25, 2017

13.7K

弱监督的深度学习模型能够从H & E染色的幻灯片中预测HER2-low.

Renan Valieris1, Luan Martins1,2, Alexandre Defelicibus1

  • 1Laboratory of Computational Biology and Bioinformatics, CIPE/A.C.Camargo Cancer Center, São Paulo, São Paulo, 01508-010, Brazil.

Breast cancer research : BCR
|August 19, 2024
PubMed
概括
此摘要是机器生成的。

一种新的深度学习方法可以准确地预测人体表皮生长因子受体2 (HER2) -低乳腺癌的状况从他的病理学图像. 这种方法为当前的HER2测试方法提供了更快,更具成本效益的替代方案,有助于临床决策.

关键词:
人工智能的人工智能是人工智能.乳腺癌是什么? 乳腺癌是什么?数字病理学数字病理学在HER2中,HER2是HER2.

更多相关视频

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

999
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

1.9K

相关实验视频

Last Updated: Jun 16, 2025

Protocol for HER2 FISH Using a Non-cross-linking, Formalin-free Tissue Fixative to Combine Advantages of Cryo-preservation and Formalin Fixation
10:21

Protocol for HER2 FISH Using a Non-cross-linking, Formalin-free Tissue Fixative to Combine Advantages of Cryo-preservation and Formalin Fixation

Published on: December 25, 2017

13.7K
Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

999
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

1.9K

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:

  • 低HER2乳腺癌是一种新发现的亚型,具有治疗意义.
  • 目前的HER2评估涉及多种测试,包括免疫组织化学和现场杂交,这可能是耗时和昂贵的.
  • 需要有效且具有成本效益的方法来确定HER2状态.

研究的目的:

  • 开发和评估一个深度学习模型,直接从基因病理图像预测HER2-低乳腺癌状态.
  • 探索不同分类模型在区分HER2-阴性,HER2-低和HER2-高乳腺癌亚型方面的性能.
  • 利用可解释的AI来识别与HER2亚型相关的组织学模式.

主要方法:

  • 采用了自我监督,基于注意力,弱监督的学习方法.
  • 通过使用来自1351名乳腺癌患者的1437张遗传病理图像,训练了六种不同的分类模型.
  • 基于注意力的模型被用于可视化和理解决策过程中感兴趣的区域.

主要成果:

  • 该研究强调了模型性能对基于测试的HER2测试对训练数据的可靠性的关键依赖.
  • 可解释的AI技术成功地确定了与不同HER2亚型相关的特定组织学模式.
  • 开发的模型证明了准确的HER2亚组分类的潜力.

结论:

  • 深度学习技术可以有效地应用于对乳腺癌中的HER2亚组状态进行分类.
  • 这种人工智能驱动的方法有可能增强瘤学家的临床决策工具包.
  • 这些发现为在乳腺癌诊断中更快,更具成本效益的HER2评估铺平了道路.