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

Regulation of Stroke Volume01:27

Regulation of Stroke Volume

7.3K
The regulation of stroke volume, which is the amount of blood the heart pumps out during each heartbeat, is critical for maintaining a healthy circulatory system. Stroke volume is influenced by three main factors: preload, contractility, and afterload.
Preload refers to the degree of stretch on the heart before it contracts. It's analogous to the stretching of a rubber band; the more it's stretched, the more forcefully it snaps back. This concept is encapsulated in the Frank-Starling law of the...
7.3K
Neural Regulation of Blood Pressure01:18

Neural Regulation of Blood Pressure

8.9K
The neural regulation of blood pressure involves intricate interactions between the autonomic nervous system (ANS) and cardiovascular system, ensuring adequate perfusion of tissues. This regulation primarily occurs through baroreceptor and chemoreceptor reflexes, involving both short-term and long-term mechanisms.
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...
8.9K

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

Green synthesis of hypericin from <i>Hypericum perforatum</i> (St. John's Wort) for photodynamic Antibacterial treatment against <i>Staphylococcus aureus</i> and <i>Escherichia coli</i>.

Natural product research·2025
Same author

Innovative modified-net architecture: enhanced segmentation of deep vein thrombosis.

Scientific reports·2024
查看所有相关文章

相关实验视频

Updated: May 4, 2026

A Multicenter MRI Protocol for the Evaluation and Quantification of Deep Vein Thrombosis
10:26

A Multicenter MRI Protocol for the Evaluation and Quantification of Deep Vein Thrombosis

Published on: June 2, 2015

18.0K

使用多模型联合学习框架与联合平均算法进行隐私意识的深静脉血栓形成细分,使用多模型联合学习框架.

Pavihaa Lakshmi B1, Vidhya S2

  • 1School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamilnadu, 632014, India.

Scientific reports
|February 26, 2026
PubMed
概括

本研究引入了联合学习 (FedL) 方法,用于使用计算机断层扫描 (CT) 扫描进行准确的深静脉血栓形成症 (DVT) 分段. FedAvg算法提高了模型性能,同时在各种数据集和客户端模型中保持了数据隐私.

关键词:
这就是为什么CTCTCTCTCTCT深静脉血栓症细分的细分联邦平均值的平均值.联合学习是联合学习.模型聚合模型聚合模型非IID数据的数据

更多相关视频

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

3.6K

相关实验视频

Last Updated: May 4, 2026

A Multicenter MRI Protocol for the Evaluation and Quantification of Deep Vein Thrombosis
10:26

A Multicenter MRI Protocol for the Evaluation and Quantification of Deep Vein Thrombosis

Published on: June 2, 2015

18.0K
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

3.6K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机科学 计算机科学

背景情况:

  • 深静脉血栓 (DVT) 诊断依赖于计算机断层扫描 (CT) 扫描的精确细分.
  • 现有的细分方法可能会面临数据隐私和分布式数据集的挑战.
  • 联合学习 (FedL) 为分散数据的培训模型提供了一种保护隐私的方法.

研究的目的:

  • 开发和评估使用CT图像进行DVT细分的高效联合学习 (FedL) 架构.
  • 为了提高细分精度和效率,同时保持数据隐私和安全.
  • 评估 FedL 框架在不同数据集大小和模型复杂度的可扩展性和稳定性.

主要方法:

  • 提出了一个高效的FedL架构,利用联邦平均化 (FedAvg) 算法.
  • 在三个阶段对非独立且相同分布的 (非IID) CT 图像进行了培训,培训了七种不同的本地模型,并增加了客户数量和模型多样性 (CNN,Sequential,Semantic,U-Net,VGG Net-19,Modified U-Net,Modified-Net).
  • 聚合本地模型权重,以逐步改进全球模型,在1000,2000和3000个样本的数据集上进行评估.

主要成果:

  • 随着数据集大小的增加,观察到显著的性能增长,包括更高的准确性和F1得分,并减少了Tversky Loss.
  • 在所有阶段都得到了持续的改进,验证损失从0.910减少到0.061.
  • 框架展示了可扩展性,增加了通信成本 (14 MB至3279 MB) 和培训时间 (7.67秒至18,702秒),同时保持了差异性隐私并改善了客户端异质性.

结论:

  • 拟议的FedL框架有效地提高了CT图像上的DVT细分精度和效率.
  • 该架构在异质环境中展示了强大的可扩展性,稳定性和差异性隐私保护.
  • 联合学习是一种可行的方法,用于在分布式环境中保护隐私的医疗图像分析.