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

PathoSyn: Imaging-Pathology MRI Synthesis via Disentangled Deviation Diffusion.

IEEE journal of biomedical and health informatics·2026
Same author

A Dual-branch Network with Cross-scale Feature Interaction and Alignment for Weakly Supervised Whole Slide Image Analysis.

IEEE journal of biomedical and health informatics·2026
Same author

Decouple, Collaborate, Match: Prototype-Driven Cognitive Mutual Learning for Brain Tumor Segmentation.

IEEE journal of biomedical and health informatics·2026
Same author

Jujuboside A-Loaded Exosomes Alleviate Pulmonary Fibrosis via TGF-β/Smad and Autophagy Regulation.

Tissue engineering. Part A·2026
Same author

Research on dynamic analysis and optimization algorithms for large-scale power systems.

Scientific reports·2026
Same author

Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

相关实验视频

Updated: May 22, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

以原型的对比网络进行医学图像分类的分散学习.

Zhantao Cao1,2,3, Yuanbing Shi1,2, Shuli Zhang1

  • 1Institutions for Research, CETC Cyberspace Security Technology CO., LTD., Chengdu, China.

Medical physics
|March 16, 2025
PubMed
概括

本研究引入了一种新的去中心化学习方法,使用原型的对比网络来提高医学图像分类准确性. 该方法有效地解决了非独立和相同分布 (非IID) 数据集和数据不平衡所带来的挑战.

关键词:
分散式的学习学习是分散式的学习.联合学习的联合学习医学图像分类 医学图像分类一个原型的对比词.

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

2.6K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

相关实验视频

Last Updated: May 22, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K
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

2.6K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

科学领域:

  • 人工智能的人工智能
  • 机器学习 机器学习
  • 医疗成像医学成像

背景情况:

  • 深层卷积神经网络 (CNN) 在医学图像分类方面表现有前途.
  • 实际应用受到非独立和相同分布的 (非IID) 数据集和数据不平衡的阻碍.
  • 隐私问题限制了来自多个机构的集中数据集的使用.

研究的目的:

  • 为准确的医疗图像分类提供一种新的去中心化学习方法.
  • 解决不同客户之间非IID数据和数据不平衡的挑战.
  • 用一个原型的对比网络来缓解非IID问题.

主要方法:

  • 开发了一个对比网络的原型,以最大限度地减少异质客户之间的差异.
  • 利用近似的全球原型将数据投射到平衡的原型空间,减轻非IID问题.
  • 使用不同的数据集验证了算法:EyePACS,APTOS,IDRiD (糖尿病视网膜病变) 和COVIDx (胸部X射线).

主要成果:

  • 在EyePACS数据集 (平衡的IID设置) 上,精度超过FedAvg基线3.7%.
  • 在EyePACS的Dirichlet非IID设置中,与FedAvg相比,实现了6.6%的精度提升.
  • 在多个指标的DCC非IID和COVID-19数据集上建立了新的最先进的性能.

结论:

  • 原型的对比性损失使本地客户端数据分布与全球分布保持一致.
  • 一个近似的全球原型通过将数据投射到平衡的空间来解决不平衡的数据分布.
  • 该模型在EyePACS,APTOS,IDRiD和COVIDx数据集上取得了最先进的结果.