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

Protective role of miR-712-3p in heatstroke-induced brain injury: involvement of neuronal lysosomal function and association with astrocytic exosome-enriched preparations.

Frontiers in pharmacology·2026
Same author

Downregulation of miR-194-5p impairs cardiomyocyte proliferation and differentiation through targeting Fign in congenital heart disease.

Molecular and cellular biochemistry·2026
Same author

Gonadal Transcriptome Analysis Reveals the lncRNA-mRNA Pair in Sea Cucumber <i>Holothuria leucospilota</i>.

Genes·2025
Same author

Unlocking Antimicrobial Peptides from Marine Invertebrates: A Comprehensive Review of Antimicrobial Discovery.

Antibiotics (Basel, Switzerland)·2025
Same author

Retraction notice to "Degradable UV-crosslinked hydrogel for the controlled release of triclosan with reduced cytotoxicity" [Mater. Sci. Eng. C, 67 (2016), 151-158].

Biomaterials advances·2025
Same author

Therapeutic hypothermia for neonates: a bibliometric analysis and visualization research.

Frontiers in neurology·2025

相关实验视频

Updated: Sep 8, 2025

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

446

多中心和小数据单细胞图像分析的元学习方法.

Lingzhi Ye1, Wentao Wang2, Hang Sun1

  • 1Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518017, China.

Analytical chemistry
|July 31, 2025
PubMed
概括

这项研究引入了用于单细胞图像分析的元学习方法,大大降低了数据标签工作量和成本. 这种新的平台即使在有限的数据中也能实现高精度,超过了传统的深度学习方法.

更多相关视频

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging
09:56

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

6.7K
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

2.2K

相关实验视频

Last Updated: Sep 8, 2025

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

446
Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging
09:56

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

6.7K
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

2.2K

科学领域:

  • 生物医学成像技术 生物医学成像技术
  • 人工智能的人工智能
  • 细胞生物学 细胞生物学

背景情况:

  • 基于算法的单细胞成像对于分析细胞异质性至关重要,但由于高标签工作量和数据可变性而面临局限性.
  • 现有的方法难以处理多种细胞来源,需要大量的手动数据注释.

研究的目的:

  • 开发一种超级学习方法,用于高效的多中心和小数据单细胞图像分析.
  • 为了减少与单细胞图像数据标签相关的手工工作量和成本.
  • 为了提高不同数据源的细胞异质性分析的准确性和稳定性.

主要方法:

  • 开发了一个硬件和软件系统,将元学习与自动化广场光显微镜集成在一起.
  • 利用元学习在多个数据中心中提取相关信息,最大限度地减少了对广泛标签的需求.
  • 通过对公共数据集的知识迁移实验验证实平台的稳定性.

主要成果:

  • 使用仅60%的标记单细胞图像数据,实现了大约92%的分类准确性,而传统深度学习则为100%.
  • 超级学习平台超过了传统的深度学习准确度,即使仅占数据量5%的数据.
  • 通过知识迁移,在各种研究环境和数据源中证明了稳定性和适用性.

结论:

  • 拟议的超级学习平台显著降低了单细胞图像数据标签工作量和成本,同时提高了效率.
  • 与传统的深度学习方法相比,该系统提供了更高的准确性和稳定性,特别是在小数据和多中心场景中.
  • 这种方法提供了一个可扩展和可靠的解决方案,用于分析来自不同来源的细胞异质性.