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

Survival Tree01:19

Survival Tree

463
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
463

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

A multidimensional core set development of sesame germplasm leveraging agro-morphological traits diversity for genetic improvement and climate resilience.

Scientific reports·2026
Same author

Integrating morphological and molecular diversity to develop high-biomass fodder pearl millet composites.

Frontiers in plant science·2026
Same author

Comparative outcomes of anterior-posterior versus posterior-only approaches for lumbosacral chordoma: A meta-analysis of recurrence, survival, and complications.

Neurosurgical review·2026
Same author

Immunogenicity and efficacy of an mRNA vaccine expressing a virus-like particle spike antigen against SARS-CoV-2.

NPJ vaccines·2025
Same author

Low-rank distribution embedding of dynamic thermographic data for breast cancer detection.

Journal of thermal biology·2025
Same author

ClinSegAI: A post-processing framework for superior histopathology segmentation accuracy, radiomics feature preservation, and quantitative analysis.

Computers in biology and medicine·2025

相关实验视频

Updated: Mar 18, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.7K

在深度分类器中通过扰乱忠实性进行强大的胰腺病理学亚型化.

Meghdad Sabouri Rad1, Junze Vincent Huang2, Mohammad Mehdi Hosseini1

  • 1Department of Pathology, SUNY Upstate Medical University, 13210, Syracuse, USA.

Journal of imaging informatics in medicine
|March 17, 2026
PubMed
概括

这项研究引入了基于深度学习的肺腺癌亚型强大的新框架,显著提高了准确性,并减少了从整个幻灯片图像中分类侵入性亚型的错误.

关键词:
注意力机制注意力机制数字病理学数字病理学肺癌的亚型分类 肺癌的亚型分类利率的一致性扰乱 忠诚度 混乱 忠诚度强大的深度学习分类.

更多相关视频

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:58

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

1.2K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

257

相关实验视频

Last Updated: Mar 18, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.7K
DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:58

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

1.2K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

257

科学领域:

  • 计算病理学计算病理学
  • 医学成像分析分析 医学成像分析
  • 人工智能在瘤学中的应用

背景情况:

  • 对侵入性肺腺癌亚型的深度学习模型容易受到现实世界成像变化的影响.
  • 准确的亚型确定对于有效的肺癌治疗和预后至关重要.

研究的目的:

  • 开发一个强大的深度学习框架,用于抗成像干扰的侵袭性肺腺癌亚型.
  • 为了提高全幻灯片图像的自动化亚型的准确性和可靠性.

主要方法:

  • 实施了保证利的一致性框架,整合了注意力加权聚合和保证利意识培训.
  • 引入了带有贝叶斯优化的参数的扰乱忠实度评分,以减轻特征过度集群.
  • 在BMIRDS-LUAD数据集上对视觉变压器-大和ResNet101模型进行了评估.

主要成果:

  • 在视觉变压器-大 (40%) 和ResNet101 (50%) 的分类精度中实现了显著的错误减少.
  • 证明了强大的特征-逻辑空间对齐与高的肯德尔相关性 (0.88培训,0.64验证).
  • 在所有五个子类型中都取得了出色的性能,ROC曲线下的面积超过0.99.

结论:

  • 拟议的边际一致性框架提高了肺腺癌亚型化深度学习的稳定性和准确性.
  • 该方法对临床应用有希望,尽管需要进行领域适应研究,以解决机构间的绩效差异.