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

相关实验视频

Updated: Mar 12, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

8.2K

基于任务的患者数据采样,用于严格的机器学习/人工智能性能评估.

Natalie Baughan1,2, Heather M Whitney3, Karen Drukker3

  • 1Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA. nbaugha1@hfhs.org.

Journal of imaging informatics in medicine
|March 10, 2026
PubMed
概括

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

Physics-informed data augmentation to simulate low dose CT scans: Application to lung nodule detection.

Medical physics·2026
Same author

Generalizations of the Jaccard index and Sørensen index for assessing agreement across multiple readers in object detection and instance segmentation in biomedical imaging.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Ethical Responsibility in the Off-Label Use of AI in Medical Imaging.

The Journal of clinical ethics·2026
Same author

Synthetic data in radiological imaging: current state and future outlook.

BJR artificial intelligence·2026
Same author

Using a Physics-Based Approach to Standardize Radiomics Values: Experimental Validation in an Anthropomorphic Phantom on a Clinical CT Scanner Using a Range of Dose Levels and Reconstruction Kernels.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

A Generative Model of Lung CT Conditioned on Radiomics Features.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same journal

OpenDicomViewer: A Lightweight Open-Source DICOM Viewer for macOS Built with Swift.

Journal of imaging informatics in medicine·2026
Same journal

Multimodal Large Language Model for Zero-Shot L3 Body Composition Segmentation on CT: Improved Accuracy via Automated Candidate Selection.

Journal of imaging informatics in medicine·2026
Same journal

Scalable Left Ventricular ROI Annotation for Stress Perfusion Cardiac MRI using Deep Learning with Visual Refinement.

Journal of imaging informatics in medicine·2026
Same journal

RE-LIG: A Faithfulness-Driven Layer Integrated Gradients Framework for Explainable Medical Visual Question Answering.

Journal of imaging informatics in medicine·2026
Same journal

Bridging Parallel Disciplines: An Integrated Workshop for Clinical and Imaging Informatics Training.

Journal of imaging informatics in medicine·2026
Same journal

CRAF-Net: A Fine-Grained Cross-Channel Attention Network for Preoperative Microvascular Invasion Grading in Hepatocellular Carcinoma via DCE-MRI.

Journal of imaging informatics in medicine·2026
查看所有相关文章
此摘要是机器生成的。

一个新的基于任务的采样算法有助于创建具有代表性的AI培训数据集. 这种方法通过将数据与预期的患者群体相匹配来减少采样偏差,以改善AI性能评估.

科学领域:

  • 医疗信息学医学信息学
  • 医疗保健中的人工智能
  • 数据科学是数据科学.

背景情况:

  • 人工智能算法性能评估需要独立的数据集,代表预期的临床人群.
  • 使用所有可用的数据可能是不切实际的,可能会引入抽样偏差.
  • 代表性数据对于可靠的AI模型培训和验证至关重要.

研究的目的:

  • 开发和演示基于任务的数据采样从大型存储库的计算方法.
  • 为AI绩效评估生成与特定的人口和临床资料相匹配的数据集.
  • 为了减轻人工智能算法开发和评估中的抽样偏差.

主要方法:

  • 开发了一个基于任务的采样算法,要求用户定义初始队列,目标分布和允许偏差.
  • 该算法应用于医学成像和数据资源中心 (MIDRC) 的数据共享.
  • 人口特征和疾病状况被用作临床属性来匹配预期的人口资料 (例如,CDC的人口统计数据).

主要成果:

  • 该算法成功地从初始>4000患者队列中取样队列 (542和870名患者).
  • 抽取的队列与目标人口分布密切匹配,平均临床属性差异较低 (1.0%和2.1%).
  • 该方法在生成用于AI绩效评估的匹配样本方面表现出有效性.
关键词:
算法的性能算法的性能.减轻偏见的偏见数据采样数据采样图像数据库 图像数据库 图像数据库机器学习是机器学习.

更多相关视频

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

2.7K

相关实验视频

Last Updated: Mar 12, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

8.2K
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

2.7K

结论:

  • 开发的基于任务的采样算法有效地从大型数据集中生成匹配的样本.
  • 这种方法减少了采样偏差,提高了人工智能算法培训和绩效评估的可靠性.
  • 该方法为在医学AI研究中创建代表性数据集提供了有价值的工具.