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

A fundus image dataset for intelligent diabetic retinopathy system.

Scientific data·2026
Same author

Developmental changes of the white matter functional connectome.

Molecular psychiatry·2026
Same author

Geometric Microstructural Characteristics of White Matter Differentiate Patients With Facial Dyskinesias and Palsy.

CNS neuroscience & therapeutics·2026
Same author

Neuroimaging and Transcriptomic Insights Into Iron Accumulation and Glymphatic Dysfunction in Olfactory Dysfunction.

CNS neuroscience & therapeutics·2026
Same author

Deciphering the molecular tapestry of schizophrenia: integrating transcriptomics, neuroimaging, and clinical data for precision medicine.

Translational psychiatry·2025
Same author

Gene expression and gray matter volume changes in Post-COVID-19 olfactory dysfunction: a transcriptomic-neuroimaging study.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2025

相关实验视频

Updated: Jul 10, 2025

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
06:57

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection

Published on: September 22, 2023

1.0K

增强多中心图形卷积网络用于COVID-19诊断.

Xuegang Song1, Haimei Li2, Wenwen Gao3

  • 1Health Science Center, School of Biomedical EngineeringShenzhen University Shenzhen 518060 China.

IEEE transactions on industrial informatics
|November 20, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个增强的多中心图卷积网络 (AM-GCN),用于从胸部CT扫描中诊断2019年新冠病毒 (COVID-19). 这种新的方法通过解决医疗中心之间的数据异质性来实现高准确性.

关键词:
冠状病毒2019年 (COVID-19) 诊断诊断情况数据增强数据增强图形卷积网络 (GCN) 是一个图形卷积网络.多中心数据集是多中心数据集.

更多相关视频

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

7.9K
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

相关实验视频

Last Updated: Jul 10, 2025

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
06:57

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection

Published on: September 22, 2023

1.0K
Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

7.9K
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

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 图形神经网络 图形神经网络

背景情况:

  • 对2019年新冠肺炎 (COVID-19) 诊断的胸部计算机断层扫描 (CT) 扫描通常来自不同的多中心数据集,采用不同的获取协议.
  • 这种中心间的异质性对开发强大的诊断模型构成了重大挑战.
  • 从多个中心整合数据对于增加样本大小和概括性至关重要.

研究的目的:

  • 开发一种有效的方法来诊断COVID-19从多中心胸部CT扫描.
  • 解决和减轻医疗成像数据集中中心间异质性的问题.
  • 为了提高AI驱动的COVID-19诊断的准确性和可靠性.

主要方法:

  • 使用带有幽灵模块和多任务框架的3D卷积神经网络,从CT扫描中提取初始特征.
  • 提取的特征被用来构建一个多中心图,考虑中心间异质性和疾病状态.
  • 使用增强机制创建了一个增强的多中心图形,用于训练图形卷积网络 (GCN).

主要成果:

  • 拟议的增强多中心图形卷积网络 (AM-GCN) 在诊断COVID-19中实现了97.76%的平均准确性.
  • 该模型在一个大型数据集上得到验证,包括来自七个医疗中心的2223名COVID-19受试者和2221名正常对照.
  • 开发的方法有效地处理来自不同医疗机构的数据异质性.

结论:

  • AM-GCN模型在使用多中心胸部CT数据诊断COVID-19时表现出高性能和稳定性.
  • 该方法成功地解决了医学成像AI中中心间异质性的挑战.
  • 公开可用的代码有助于进一步研究和临床应用这种诊断工具.