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

[Chemical constituents from a Tibetan medicine Meconopsis horridula].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2014
Same author

[Chemical constituents from whole plants of Aconitum tanguticum (III)].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2014
Same author

Plasma metabonomics study on Chinese medicine syndrome evolution of heart failure rats caused by LAD ligation.

BMC complementary and alternative medicine·2014
Same author

A versatile complementation assay for cell-to-cell and long distance movements by cucumber mosaic virus based agro-infiltration.

Virus research·2014
Same author

Composition of EPS fractions from suspended sludge and biofilm and their roles in microbial cell aggregation.

Chemosphere·2014
Same author

CXCL9 and CXCL10 accelerate acute transplant rejection mediated by alloreactive memory T cells in a mouse retransplantation model.

Experimental and therapeutic medicine·2014

相关实验视频

Updated: Jul 6, 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

2.8K

基于有限的医学图像数据的半监督疾病分类.

Yan Zhang, Chun Li, Zhaoxia Liu

    IEEE journal of biomedical and health informatics
    |January 8, 2024
    PubMed
    概括

    这项研究引入了一种新的生成模型,用于使用积极和未标记的医学图像进行半监督疾病分类. 霍尔德基于分歧的模型在五个基准数据集上取得了最先进的结果,超过了现有的方法.

    科学领域:

    • 医学图像分析 医学图像分析
    • 机器学习 机器学习
    • 计算机辅助诊断 计算机辅助诊断

    背景情况:

    • 具有积极和未标记 (PU) 数据的半监督学习在医学成像中具有挑战性,因为标记数据有限.
    • 现有的方法在疾病分类中难以获得注释医疗图像.
    • 医学图像辅助诊断的PU学习对于减少专家工作量至关重要.

    研究的目的:

    • 使用PU医学图像数据开发一种用于半监督疾病分类的新型生成模型.
    • 在分类任务中解决有限的标记医疗图像所带来的挑战.
    • 提高医学影像辅助诊断的准确性和效率.

    主要方法:

    • 介绍了一种新型的生成模型,灵感来自于PU学习的霍尔德分歧.
    • 综合问题制定和理论可行性分析.
    • 在五个基准医学图像数据集 (乳腺MNIST,肺炎MNIST,血液MNIST,OCTMNIST,AMD) 上进行了广泛的实验.

    主要成果:

    • 提出的霍尔德基于分歧的模型显著优于现有的基于分歧的KL方法.
    • 这种新的方法在所有五个测试的疾病分类基准中都实现了最先进的性能.
    • 在利用未标记的医疗图像以改善分类方面表现出优越性.

    更多相关视频

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
    07:15

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

    Published on: August 16, 2020

    6.8K
    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

    Published on: October 10, 2018

    8.3K

    相关实验视频

    Last Updated: Jul 6, 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

    2.8K
    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
    07:15

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

    Published on: August 16, 2020

    6.8K
    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

    Published on: October 10, 2018

    8.3K

    结论:

    • 这种新型的生成模型为半监督疾病分类提供了一个有希望的解决方案,使用有限的标记医疗数据.
    • 霍尔德分歧方法有效利用未标记的数据,增强医学图像分析.
    • 这种方法代表了医学影像辅助诊断领域的重大进步.