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

Structure-aware fatigue modeling in foot deformities: A digital health framework for tissue-specific running injury risk prediction using multi-modal data.

PLOS digital health·2026
Same author

Spatiotemporal inequities in early-life ecological liveability and sleep health in preschool children.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Understanding the "how" and "why": A mixed methods process evaluation for the PRO-HIIT intervention.

PloS one·2026
Same author

Interlimb differences in knee joint loading and stress distribution following anterior cruciate ligament reconstruction during stair descent.

Clinical biomechanics (Bristol, Avon)·2026
Same author

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

HSPA6 Confers Lenvatinib Resistance in Hepatocellular Carcinoma by Promoting Phase Separation-Mediated TXNRD1 Stabilization to Suppress Ferroptosis.

Cancer research·2026

相关实验视频

Updated: Jul 1, 2025

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors
11:15

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

24.4K

对肺腺癌亚型的基于变压器的模型.

Fawen Du1, Huiyu Zhou2, Yi Niu1

  • 1School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China.

Medical physics
|March 1, 2024
PubMed
概括

本研究介绍了HybridNet,这是一种用于将肺腺癌 (LAD) 分类为五种组织学亚型的新型深度学习模型. 混合网络实现了高精度,有助于个性化癌症治疗和预后.

关键词:
功能融合的特点是:组织学亚型 组织学亚型肺部腺癌瘤是肺部腺癌.多重分类是多重分类的一个方法.自己注意的注意力.

更多相关视频

Multidimensional Coculture System to Model Lung Squamous Carcinoma Progression
07:53

Multidimensional Coculture System to Model Lung Squamous Carcinoma Progression

Published on: March 17, 2020

7.2K
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

10.2K

相关实验视频

Last Updated: Jul 1, 2025

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors
11:15

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

24.4K
Multidimensional Coculture System to Model Lung Squamous Carcinoma Progression
07:53

Multidimensional Coculture System to Model Lung Squamous Carcinoma Progression

Published on: March 17, 2020

7.2K
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

10.2K

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:

  • 全球肺癌患病率和死亡率最高.
  • 组织学亚型对于肺癌诊断,预后和治疗反应预测至关重要.
  • 现有的方法无法捕捉肺腺癌 (LAD) 组织亚型的细微特征.

研究的目的:

  • 率先将LAD分为五种不同的组织学亚型进行分类:状,斑状,微毛状,毛状和固体.
  • 开发和验证一个新的深度学习模型,HybridNet,以改进LAD亚型分类.

主要方法:

  • 混合网络采用双流架构,集成全球表示的变压器和局部特征的卷积神经网络 (CNN).
  • 变压器中的自我注意力机制捕获丰富的上下文信息.
  • 两个流的特征地图被交互融合,以增强分类的区分能力.

主要成果:

  • 在私人LAD数据集上,HybridNet实现了95.12%的整体分类准确性.
  • 个别亚型的准确性是:状 (94.5%),斑状 (97.1%),微毛囊状 (94%),毛囊状 (91%) 和固体 (99%).
  • 该模型在公开的BreakHis数据集上表现出强的表现,在准确性 (92.40%),回忆力 (90.63%) 和F1得分 (91.43%) 方面取得了最佳结果.

结论:

  • 将LAD分为五种亚型有助于病理学家选择治疗,预测瘤突变负担 (TMB) 和免疫检查点蛋白质分析.
  • 混合网络有效地融合了CNN和变压器的功能,大大提高了亚型分类的准确性.
  • 该模型在公共数据集上表现出令人满意的概括能力,表明其潜在的临床实用性.