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

Spatial transcriptomic analyses highlight distinct erythroid niches in mice and humans.

Nature genetics·2026
Same author

Inferring DNA Methylation Class from Digitized Pathology Images and AI: A Worthy and Timely Application with Room for Improved Clinical Performance.

Neuro-oncology·2026
Same author

Effects of breast cancer risk factors on the tumor microenvironment: a morphological deep-learning analysis of three prospective cohorts.

NPJ breast cancer·2026
Same author

Artificial Intelligence in Oncology: Clinical Applications, Challenges, and Opportunities.

American Society of Clinical Oncology educational book. American Society of Clinical Oncology. Annual Meeting·2026
Same author

Machine learning identification of maternal inflammatory response and systemic inflammatory response from placental membrane whole slide images.

Placenta·2026
Same author

Stromal Gasdermin D-mediated Pyroptosis Drives Maladaptive CD4<sup>+</sup> T-cell Remodeling in Tet2-Deficient Hematopoiesis.

bioRxiv : the preprint server for biology·2026

相关实验视频

Updated: Jul 6, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K

从人群中学习自动化基因病理图像细分.

Miguel López-Pérez1, Pablo Morales-Álvarez2, Lee A D Cooper3

  • 1Department of Computer Science and Artificial Intelligence, University of Granada, Spain.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
|January 9, 2024
PubMed
概括

这项研究介绍了一种可扩展的众包方法,用于对基因病理图像进行细分,通过高效地建模注释者专业知识来提高准确性. 与专家标记的数据相比,新方法取得了竞争力的结果.

关键词:
癌症 癌症 癌症 癌症众包服务 (crowdsourcing) 是一种众包服务.组织病理学 组织病理学噪音很大的标签分段化 分段化 分段化 分段化

更多相关视频

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K
Automated Quantification of Hematopoietic Cell &#8211; Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.6K

相关实验视频

Last Updated: Jul 6, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K
Automated Quantification of Hematopoietic Cell &#8211; Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.6K

科学领域:

  • 计算病理学计算病理学
  • 医学图像分析 医学图像分析
  • 机器学习 机器学习

背景情况:

  • 基因病理图像的自动语义细分对于计算病理学 (CPATH) 是至关重要的.
  • 深度学习 (DL) 方法受到专家注释的稀缺性所限制.
  • 众包 (CR) 提供了一个解决方案,但面临着杂的挑战,非专家的注释.

研究的目的:

  • 开发一种可扩展的众包方法,用于基因病学图像细分.
  • 共同学习专家细分和注释者专业知识,而无需培训每个注释者的单独模型.
  • 为了解决现有方法的局限性,这些方法不能使用大量注释符进行缩放.

主要方法:

  • 提出了一种使用两个结合的神经网络的新方法家族:分段网络和注释器网络.
  • 标注器网络使用一个单一的网络来估计标注器行为,该网络将标注器ID作为输入,从而实现可扩展性.
  • 引入了一个新的注释器网络模型,考虑全球图像特征,以改进专业估计.

主要成果:

  • 拟议的CR建模在三阴性乳腺癌图像上实现了0.7827的子系数.
  • 超过了已建立的STAPLE算法 (0.7039).
  • 与使用专家标签 (0.7723) 的监督方法相比,已证明具有竞争力的性能.

结论:

  • 开发的合网络方法为众包 histopathological 图像细分提供了可扩展和有效的解决方案.
  • 这种方法成功地模拟了注释者专业知识和细分,克服了以前非可扩展方法的局限性.
  • 这些发现表明,利用众包在现实世界的计算病理学应用中是一个可行的途径.