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

Positron Emission Tomography01:29

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body being...

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

Pelvic venous disorders in women: Diagnosis and management for gynecologists.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2026
Same author

Integrating equity into incident reporting and patient concerns systems: a critical interpretive synthesis.

BMJ quality & safety·2025
Same author

Efficient Detection of Stigmatizing Language in Electronic Health Records via In-Context Learning: Comparative Analysis and Validation Study.

JMIR medical informatics·2025
Same author

Systems Factors Contributing to Racial/Ethnic Disparities in Maternal Health: A Systematic Review.

Journal of racial and ethnic health disparities·2025
Same author

Imaging-Based Approach to Venous-Origin Chronic Pelvic Pain.

Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes·2025
Same author

Examining the development, effectiveness, and limitations of computer-aided diagnosis systems for retained surgical items detection: a systematic review.

Ergonomics·2025

相关实验视频

Updated: Jun 29, 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

42.8K

性能,可解释性和公平性在神经原型树的交叉点,用于胸部X射线病理检测:算法开发和验证研究.

Hongbo Chen1, Myrtede Alfred1, Andrew D Brown2

  • 1Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada.

JMIR formative research
|December 5, 2024
PubMed
概括

本研究介绍了用于胸部X射线 (CXR) 病理检测的神经原型树 (NPT) 分类器,提高了深度学习的透明度. NPT分类器表现出更好的性能和公平性,增加了可解释性,为临床环境提供了一个有前途的工具.

关键词:
胸部X射线 胸部X射线 胸部X射线深度学习是一种深度学习.可解释的人工智能公平的公平的公平.可以解释的解释性.胸部病理学 胸部病理学

更多相关视频

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

648
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

229

相关实验视频

Last Updated: Jun 29, 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

42.8K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

648
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

229

科学领域:

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

背景情况:

  • 深度学习模型在胸部X射线 (CXR) 分析中实现了高精度,但缺乏透明度,阻碍了临床采用.
  • 神经原型树 (NPT) 作为一个可解释的分类器,将深度学习的诊断能力与CXR病理检测的决策树可解释性相结合.

研究的目的:

  • 评估神经原型树 (NPT) 分类器在CXR病理检测中的性能,可解释性和公平性.
  • 检查这三个维度之间的相互作用,并强调NPT分类器的本地和全球解释.

主要方法:

  • 使用胸部X射线14,CheXpert和MIMIC-CXR数据集进行训练.
  • 与一个基线ResNet-152与五个NPT分类器进行了比较,分别具有不同的解释性级别.
  • 使用线性回归分析测量性能 (ROC AUC),可解释性 (IC) 和公平性 (TPR平均差异).

主要成果:

  • 随着可解释性的提高,NPT分类器的性能提高了,在数据集的特定IC级别上超过了ResNet-152.
  • 较低的解释性 (IC 1级) 与较高的不公平性相关 (TPR平均差异),特别是在基于年龄的子组中.
  • 在解释性和性能 (ROC AUC) 之间发现了显著的积极关系,在解释性和公平性 (平均TPR差异) 之间发现了负面关系.

结论:

  • 在CXR病理检测中,NPT分类器提供了性能,可解释性和公平性之间的平衡.
  • 研究结果为开发有效,可解释和公平的医学成像深度学习模型提供了洞察力.
  • 该研究强调了透明AI在放射学中的潜在临床实用性.