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

miRNA profiling reveals that gga-let-7i/COL1A2 axis induces cell cycle arrest and triggers cellular senescence to accelerate ovarian aging in laying hens by suppressing the PI3K/AKT/MDM2 pathway.

Poultry science·2026
Same author

Phenothiazine-based anodes with π-conjugation extension and dynamic charge balance enabling ultra-stable hydronium-ion batteries.

Chemical communications (Cambridge, England)·2026
Same author

Design, Simulation and High Precision Tracking Control of a Piezoelectric Optical Stabilization Platform.

Micromachines·2026
Same author

Pulmonary Solid and Granular Adenocarcinomas Expressing HepPar1/CPS1: Highly Aggressive Tumors Exhibiting Mitochondrial Adaptation to STK11 Mutations Rather Than Hepatoid Differentiation.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same author

Comparing the predictive accuracy of life's essential 8 and life's crucial 9 scores for all-cause mortality in COPD patients among US adults: a prospective cohort study.

BMC public health·2026
Same author

Andrographolide targets syndecan4 to impair its interaction with syntenin and inhibits the biogenesis of small extracellular vesicles.

The Journal of biological chemistry·2026

相关实验视频

Updated: Jun 29, 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

2.7K

通过分子授权学习,通过普通注释器实现病态图像分割的民主化.

Ruining Deng1, Yanwei Li1, Peize Li1

  • 1Vanderbilt University, Nashville TN 37215, USA.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 26, 2024
PubMed
概括
此摘要是机器生成的。

这项研究表明,AI细胞细分模型可以有效地使用分子数据和置注释器进行训练,比专家注释更高的准确性. 这种方法使人工智能开发用于病理学任务的民主化.

关键词:
图像注释 图像注释噪音标签学习学习病理学 病理学 病理学登记 登记 登记 登记 登记

更多相关视频

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.7K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

相关实验视频

Last Updated: Jun 29, 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

2.7K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.7K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

科学领域:

  • 计算病理学计算病理学
  • 医学中的人工智能
  • 生物图像分析分析

背景情况:

  • 在全幻灯片图像 (WSI) 中精确的多类细胞细分对于临床AI应用至关重要.
  • 目前的人工智能模型培训依赖于领域专家的耗时和易出错的手动注释.
  • 在WSI中区分微妙的细胞类型对人类注释者构成挑战.

研究的目的:

  • 评估在病理性AI部署中使用普通注释者的可行性.
  • 开发一种分子授权的细胞细分学习方案,使用非专家的部分标签.
  • 民主化病理细分深度模型的开发.

主要方法:

  • 提出了一个分子授权的学习方案,用于多类细胞细分.
  • 集成的千兆像素分子形态跨模式注册和分子信息注释.
  • 对于杂的,部分注释的数据,采用了深度校正学习方法.

主要成果:

  • 获得了F1得分0.8496使用分子知情注释从客注释者.
  • 经验丰富的病理学家 (F1 = 0.7015) 的基于传统形态学的注释表现优于.
  • 与2名经验丰富的病理学家相比,与3名简单的注释者表现出卓越的表现.

结论:

  • 分子授权学习方案有效地民主化了病态AI开发,以设置注释器级别.
  • 这种方法显著提高了细胞细分的准确性和可扩展性.
  • 该方法使人工智能模型培训能够与非医疗计算机视觉任务相提并论.