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

Risk of selected immune-mediated inflammatory diseases after solid organ transplantation in a Korean nationwide cohort.

JAAD international·2026
Same author

The heart-brain geometry paradox: adaptive growth vs maladaptive remodelling.

European heart journal·2026
Same author

Behavioral mapping of multisensory experience and engagement in accessible gardens: a case study of Xuanwu Lake Park, Nanjing.

Frontiers in psychology·2026
Same author

Advances in Biomarkers and Therapeutic Targets for Idiopathic Inflammatory Myopathies Related Lung Disease.

Clinical reviews in allergy & immunology·2026
Same author

Automated segmentation and quantitative analysis of vascular curvature features in unruptured intracranial aneurysms based on time-of-flight magnetic resonance angiography (TOF-MRA).

Quantitative imaging in medicine and surgery·2026
Same author

Structural dynamics of microtubules in glioma: impact on macrophage M2 polarization and tumor cell heterogeneity.

Journal of translational medicine·2026

相关实验视频

Updated: Jul 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

对基于核细分的病态图像分类进行逆域适应.

Zhixin Xu1, Seohoon Lim1, Yucheng Lu2

  • 1Department of Electrical Engineering, Korea University, Seoul, Republic of Korea.

Computers in biology and medicine
|November 20, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了对数字病理学的反向无监督域适应,增强了深度学习模型的概括性. 该方法通过减少细分差异而改善目标域的图像分类性能,而不需要目标标签.

关键词:
深度学习是一种深度学习.医疗成像医学成像核心细分的核心细分.病理图像分类 疾病图像分类无监督的域名适应

更多相关视频

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

205
Patient-Derived Tumor Explants As a "Live" Preclinical Platform for Predicting Drug Resistance in Patients
07:42

Patient-Derived Tumor Explants As a "Live" Preclinical Platform for Predicting Drug Resistance in Patients

Published on: February 7, 2021

5.0K

相关实验视频

Last Updated: Jul 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

205
Patient-Derived Tumor Explants As a "Live" Preclinical Platform for Predicting Drug Resistance in Patients
07:42

Patient-Derived Tumor Explants As a "Live" Preclinical Platform for Predicting Drug Resistance in Patients

Published on: February 7, 2021

5.0K

科学领域:

  • 数字病理学数字病理学
  • 医疗图像分析 医学图像分析
  • 深度学习是一种深度学习.

背景情况:

  • 数字病理学在医学上提供了一个新的范式,但深度学习模型因注释不足和概括不良而扎.
  • 弱概括限制了在缺乏足够标记数据的领域中的模型性能.

研究的目的:

  • 通过域调整在数字病理学中增强深度学习模型的泛化.
  • 通过利用源域标签和核心细分来提高目标域数据的预测准确性.

主要方法:

  • 实施了反向无监督域调整策略,以在源域中产生目标类型的结果.
  • 集成核细分为分类器提供额外的诊断信息.
  • 开发了一个统一的框架,用于对细分和分类模块的联合培训.

主要成果:

  • 反向域适应有效地减少了没有目标标签的源域和目标域之间的核细分差异.
  • 在目标域中显著提高图像分类性能.
  • 在目标域分类中表现优于现有的一般域调整方法.

结论:

  • 反向无监督域适应是改善数字病理图像分类的强大策略.
  • 拟议的方法增强了模型的概括性,并减少了对广泛的目标域注释的依赖.
  • 联合训练的细分和分类模块在具有挑战性的领域提供了卓越的性能.