Jove
Visualize
联系我们

相关概念视频

Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

280
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
280

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

Prompt-Sensitive Decision Behavior of Large Language Models in Intensive Care Unit Mortality Prediction for Spontaneous Intracerebral Hemorrhage: Comparative Benchmarking Study.

Journal of medical Internet research·2026
Same author

Clinical Usefulness and Cut-Off Value of Computed Tomography-Measured Visceral Adipose Tissue in Coronary Artery Disease.

Diagnostics (Basel, Switzerland)·2026
Same author

Machine learning predictive system to predict the risk of developing pre-eclampsia.

BMJ health & care informatics·2025
Same author

Screening of Medicinal Herbs Identifies <i>Cimicifuga foetida</i> and Its Bioactive Component Caffeic Acid as SARS-CoV-2 Entry Inhibitors.

Viruses·2025
Same author

"Could She/He Walk Out of the Hospital?": Implementing AI Models for Recovery Prediction and Doctor-Patient Communication in Major Trauma.

Diagnostics (Basel, Switzerland)·2025
Same author

Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning.

Diagnostics (Basel, Switzerland)·2025
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

相关实验视频

Updated: Jan 13, 2026

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

43.6K

通过GPT-4o:算法开发和多站点内部验证来增强传统方法来检测组合放射学研究中的横向性错误.

Kung-Hsun Weng1, Yi-Chen Chou1, Yu-Ting Kuo1,2,3

  • 1Department of Medical Imaging, Chi Mei Medical Center, Tainan, Taiwan.

JMIR formative research
|October 29, 2025
PubMed
概括

一种新的基于规则和GPT-4o组合方法有效地选联合放射学报告中的横向性错误. 这种方法在真实世界数据上的表现优于其他模型,突出显示了未来研究中不平衡数据集的需要.

关键词:
人工智能的人工智能是人工智能.深度学习是一种深度学习.电子健康记录是电子健康记录.大型语言模型横向性错误是因为横向性错误.自然语言处理自然语言处理.质量保证 质量保证 质量保证无线图报告 无线图报告放射学报告 放射学报告基于规则的方法 基于规则的方法

更多相关视频

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

1.6K
Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

550

相关实验视频

Last Updated: Jan 13, 2026

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

43.6K
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

1.6K
Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

550

科学领域:

  • 医疗信息学 医疗信息学
  • 在医疗保健中的自然语言处理.
  • 放射学质量保证 质量保证

背景情况:

  • 放射学报告中的横向性错误带来了严重的患者安全风险.
  • 在综合放射性报告中发现这些错误的选方法尚不发达.

研究的目的:

  • 分析综合放射性报告格式的挑战.
  • 引入和评估一个新的组合方法 (基于规则的+GPT-4o) 用于横向性错误检测.
  • 评估现实世界不平衡和合成平衡数据集之间的性能差异.

主要方法:

  • 追溯分析了1万份未被识别的放射学报告.
  • 开发和比较基线,解决方案和GPT-4o增强的基于规则的方法.
  • 在真实世界和合成数据集上对微调的RoBERTa,ClinicalBERT和GPT-4o模型的评估.

主要成果:

  • 在真实世界报告中,横向性错误率为1.20%,在组合 (1.47%) 与非组合 (0.57%) 报告中更高.
  • 基于规则的+GPT-4o方法在不平衡的现实数据上实现了最高的回忆,超过了GPT-4o,ClinicalBERT和RoBERTa.
  • 在所有模型中,与合成平衡数据相比,在真实世界的不平衡数据上观察到精度和F1分数的显著性能下降.

结论:

  • 综合放射性报告格式为质量保证和NLP带来了独特的挑战.
  • 基于规则的+GPT-4o组合方法在检测现实世界,不平衡数据集中的横向性错误方面表现出有效性.
  • 未来的研究必须纳入现实世界的不平衡数据,以准确地比较性能.