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

Association of Thyroid Hormone Levels and Thyroid Hormone Sensitivity with Adverse Clinical Outcomes in Euthyroid Patients with Ischemic Stroke.

Current neurovascular research·2026
Same author

Ancient mitogenomes reveal the genetic relationship among extinct and extant water buffaloes.

iScience·2026
Same author

Glucosinolate-Derived Flavor Chemistry of Brassica Vegetables: Formation, Transformation, Stability, and Sensory Implications.

Comprehensive reviews in food science and food safety·2026
Same author

A straightforward framework to harmonize computational pathology.

Journal of pathology informatics·2026
Same author

Exploring the Possible Role of Gut Microbiota with Ischemic Stroke Subtypes: A Mendelian Randomization Study with Insights into Immune Cell Mediators.

Current medicinal chemistry·2026
Same author

Reliability of foundation models for image retrieval in histopathology.

Npj imaging·2026
Same journal

Serum vitamin D level and its association with vertigo frequency and severity in Meniere disease.

Scientific reports·2026
Same journal

PFA-Net: a physics-informed feature enhancement and attention network for interpretable bearing fault diagnosis under strong noise.

Scientific reports·2026
Same journal

Circulating inflammatory, redox, and apoptosis-related alterations in drug-naive idiopathic pulmonary fibrosis: an exploratory case-control study.

Scientific reports·2026
Same journal

A baseline-oriented dynamic aggregation approach for demand-side heterogeneous controllable resources.

Scientific reports·2026
Same journal

Temporal precision and accuracy in schizophrenia: an exploratory study.

Scientific reports·2026
Same journal

Prefrontal EEG spectral and nonlinear signatures of subthreshold depression during resting state and affectively valenced picture/video viewing: a participant-level analysis.

Scientific reports·2026
查看所有相关文章

相关实验视频

Updated: Jan 14, 2026

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.7K

轻量级的自我监督的学习框架,用于在组织病理学领域的泛化.

Abubakr Shafique1, Amanda Dy2, Xiaoli Qin2

  • 1Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada. abubakr.shafique@torontomu.ca.

Scientific reports
|October 21, 2025
PubMed
概括
此摘要是机器生成的。

组织病理学中的基础模型 (FMs) 是有前途的,但需要大量资源. HistoLite是一个轻量级的框架,可以实现高效的,域不变的学习,解决计算病理学的可访问性和概括性挑战.

关键词:
数字病理学数字病理学域名通用化域名通用化域名转移 域名转移域名转移基金会模型 基金会模型轻量级的模型轻量级的模型自主监督学习学习

更多相关视频

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

810
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.5K

相关实验视频

Last Updated: Jan 14, 2026

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.7K
Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

810
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.5K

科学领域:

  • 组织病理学 组织病理学
  • 计算病理学计算病理学
  • 机器学习 机器学习

背景情况:

  • 在广泛的遗传病理学数据集上训练的大型基础模型 (FMs) 显示了推进计算病理学的前景.
  • FM可以弥合培训和测试数据集之间的领域差距,改善翻译机会.
  • 然而,FM的计算和数据需求限制了其可访问性和广泛采用.

研究的目的:

  • 介绍HistoLite,一种轻量级的自我监督学习框架,用于在组织病理学中进行域不变表示学习.
  • 为了能够有效地学习通用和可转移的特征,克服大规模FM要求的局限性.
  • 评估HistoLite在使用乳腺整体幻灯片图像 (WSIs) 的域概括中的性能,并与最先进的FM相比较.

主要方法:

  • 开发了HistoLite,一个使用可定制自动编码器的自主监督学习框架.
  • 从两个不同的平台扫描的相同组织幻灯片中策划了一个新的WSI数据集,以分析扫描器偏差.
  • 使用新型指标 (稳定性指数) 评估的表示转移,并评估下游任务准确性.

主要成果:

  • 大多数FM表现出对扫描器偏差的敏感性,通过嵌入差异和性能下降在域外数据上进行指示.
  • 性能最好的FM (UNI,Virchow2,Prov-GigaPath) 很可能受到大型模型大小和训练数据集的青.
  • 在域外数据上,HistoLite表现出较低的表示转移和最小的性能退化,分类准确度适度.

结论:

  • 扫描器偏差在组织病理学中对FMs的现实世界部署构成了重大挑战.
  • HistoLite提供了一个有前途的轻量级替代品,平衡计算病理学应用的概括性和准确性.
  • 这些发现突出了模型大小,概括能力和组织病理学FMs的准确性之间的潜在权衡.