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

Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks.

Scientific reports·2025
Same author

DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision.

Journal of imaging informatics in medicine·2024
Same author

A Critical Assessment of Generative Models for Synthetic Data Augmentation on Limited Pneumonia X-ray Data.

Bioengineering (Basel, Switzerland)·2023
Same author

Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset.

Scientific reports·2023
Same author

Leveraging human expert image annotations to improve pneumonia differentiation through human knowledge distillation.

Scientific reports·2023
Same author

Time management training and perceived control of time at work.

The Journal of psychology·2010

相关实验视频

Updated: Jul 25, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K

联邦深度学习架构用于保护隐私的肺炎检测从COVID-19胸部X-ray图片.

Pascal Riedel1, Reinhold von Schwerin1, Daniel Schaudt1

  • 1Institute for Informatics, University of Applied Sciences, Prittwitzstraße 10, Ulm, 89075 Baden-Württemberg Germany.

Journal of healthcare informatics research
|June 26, 2023
PubMed
概括

联合学习与ResNetFed和差异隐私改进了从胸部X射线检测COVID-19肺炎的性能,超过了当地的模型,特别是数据分布不均.

关键词:
在 COVID-19 疫情中,深度学习是一种深度学习.联合学习是联合学习.医学成像医学成像这就是ResNet ResNet.

更多相关视频

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.9K

相关实验视频

Last Updated: Jul 25, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

1.9K

科学领域:

  • 医疗保健中的人工智能
  • 医学成像分析 医学成像分析
  • 保护隐私的机器学习

背景情况:

  • 医疗保健中的集中式机器学习面临着由于个人健康数据隐私法规的挑战.
  • 联邦学习 (FL) 提供了一个去中心化的方法,在孤立的数据上培训模型,以保持隐私.
  • 使用医学成像检测COVID-19需要准确和私密的方法.

研究的目的:

  • 调查联合学习的可行性,以检测COVID-19肺炎从胸部X射线影像.
  • 提出和评估一个保护隐私的联邦模式,ResNetFed,结合差异隐私.
  • 在不均的数据分布场景下评估联合方法的性能.

主要方法:

  • 从COVIDx8数据集中使用了1411张胸部X射线图 (753张正常,658张COVID-19).
  • 在五个模拟数据库中不均地分区数据,以模拟现实世界FL条件.
  • 开发了ResNetFed,这是一个经过修改的预训练ResNet50模型,具有差异隐私,用于联合培训.

主要成果:

  • ResNetFed的平均准确率为82.82%,明显优于本地训练的ResNet50模型 (63%的准确率).
  • 联合方法表现出卓越的性能,特别是在人口不足的数据仓库中,精度增加了高达34.9%.
  • ResNetFed有效地解决了因数据分布在孤岛之间不均而导致的绩效差异.

结论:

  • 联合学习,特别是ResNetFed和差异隐私,是COVID-19肺炎检测的可行和有效方法.
  • 拟议的联合解决方案增强了隐私,同时保持了高准确性,即使在不平衡的数据集.
  • ResNetFed提供了一种实用的,保护隐私的工具,以帮助在医疗环境中进行首次COVID-19查.