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

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

187
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
187

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 hybrid deep learning model with adaptive feature fusion for automated rice leaf disease detection and classification.

Scientific reports·2026
Same author

Cannabidiol and diabetic heart disease: Mechanistic evidence and translational challenges.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2026
Same author

Fiberoptic Bronchoscopy Monitoring During Percutaneous Dilatational Tracheostomy: A Multicenter, Randomized, Controlled Trial. The FIBERTRACH Randomized Clinical Trial.

Critical care medicine·2026
Same author

Barrier resolution via patient navigation in the context of cancer care.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026
Same author

Leveraging Social Needs Assessments to Eliminate Barriers to Diabetes Self-Management in a Vulnerable Population.

International journal of environmental research and public health·2025
Same author

Lung Cancer Screening among Adults Older than Medicare's Upper Age Eligibility Criteria.

Cancer prevention research (Philadelphia, Pa.)·2025

相关实验视频

Updated: May 17, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K

通过监督的对抗性域调整来解决胸部X射线分类中跨人口域转移的问题.

Aminu Musa1,2, Rajesh Prasad3,4, Monica Hernandez5

  • 1Deparment of Computer Science, African University of Science and Technology, Abuja, 900107, Nigeria. musa.aminu@fud.edu.ng.

Scientific reports
|April 3, 2025
PubMed
概括

医学成像中的人工智能 (AI) 面临着领域转移的挑战. 一种新的对抗领域适应技术改善了不同人群的胸部X射线分类准确性,提高了AI诊断.

更多相关视频

X-ray Dose Reduction through Adaptive Exposure in Fluoroscopic Imaging
08:30

X-ray Dose Reduction through Adaptive Exposure in Fluoroscopic Imaging

Published on: September 11, 2011

14.3K
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

979

相关实验视频

Last Updated: May 17, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
X-ray Dose Reduction through Adaptive Exposure in Fluoroscopic Imaging
08:30

X-ray Dose Reduction through Adaptive Exposure in Fluoroscopic Imaging

Published on: September 11, 2011

14.3K
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

979

科学领域:

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

背景情况:

  • 人工智能 (AI) 对于医疗保健中的医学图像分析至关重要.
  • 机器学习模型在领域转移方面扎,限制了跨不同患者群体的概括.
  • 胸部X射线分类面临的挑战是由于跨种群的变化,特别是代表性不足的群体.

研究的目的:

  • 为了调查不同人群的胸部X射线分类领域转移问题.
  • 提出和评估一个监督的对抗性域调整 (ADA) 技术,以解决跨人群的域转移问题.
  • 改善AI模型在代表性不足的数据集上的性能.

主要方法:

  • 分析了使用三个来源人口数据集和尼日利亚胸部X射线数据集作为目标的域转移影响.
  • 开发了一种监督对抗域适应 (ADA) 方法,涉及特征提取器和对抗域区分器.
  • 在源域上训练了特征提取器,并使用对抗训练来创建域不变特征.

主要成果:

  • 当在源域上训练的模型应用于目标尼日利亚数据集时,观察到显著的性能差异.
  • 拟议的ADA技术在尼日利亚数据集上的胸部X射线分类方面取得了实质性的改进.
  • 该模型实现了90.08%的准确性和96%的AUC,超过了多任务学习 (MTL) 和持续学习 (CL).

结论:

  • 领域转移对AI在医学成像中构成重大挑战,特别是在多样化的人口中.
  • 监督对抗域适应 (ADA) 有效地创建域不变的特征,减轻跨人群的差异.
  • 开发具有领域意识的AI模型对于公平有效的医疗保健诊断至关重要.