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 authorSame journal

Multimodal LLM vs. Human-Measured Features for AI Predictions of Autism in Home Videos.

Algorithms·2026
Same authorSame journal

Ensemble Modeling of Multiple Physical Indicators to Dynamically Phenotype Autism Spectrum Disorder.

Algorithms·2026
Same author

Remote Assessment of Parkinson Disease Using Deep Learning on Structured Mouse-Trace Data From Suspected Cases: Machine-Learning Pilot Feasibility Study.

JMIR formative research·2026
Same author

The effect of distributional information on the categorization of unaccusativity.

Journal of child language·2026
Same author

Correlates of Fitness Tracker Ownership and Use in Cancer Survivors: Cross-Sectional Survey.

JMIR cancer·2026
Same author

Personalized modeling of stress and blood pressure reactivity using mobile health data.

Npj mental health research·2026

相关实验视频

Updated: Jun 22, 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

2.7K

减少偏见的挑战 使用后处理公平性用于深度学习的乳腺癌阶段分类.

Armin Soltan1, Peter Washington1

  • 1Hawaii Health Digital Lab, Information and Computer Science, University of Hawaii at Manoa, Honolulu, HI 96822, USA.

Algorithms
|July 4, 2024
PubMed
概括

乳腺癌的深度学习模型显示偏差,由于培训数据中的代表性不足,在白人患者中表现更好. 后处理校准在实现公平性方面产生了不同的结果.

科学领域:

  • 医疗成像医学成像
  • 医疗保健中的人工智能
  • 在瘤学瘤学.

背景情况:

  • 乳腺癌是全球女性的主要健康问题.
  • 深度学习模型在乳腺癌诊断和治疗方面表现有前途.
  • 确保AI模型在不同人群中的公平性是一个重大挑战,特别是在培训数据中代表性不足的人口群体.

研究的目的:

  • 在用于乳腺癌分期的深度学习模型中量化偏差.
  • 评估后处理校准在缓解已识别的偏差方面的有效性.

主要方法:

  • 训练深度学习模型来预测乳腺癌的阶段,使用来自842名患者的1000个活检的数据集.
  • 该数据集主要包括来自白人患者的数据 (超过70%).
  • 在校准前后评估白人和非白人患者组之间的模型性能差异.

主要成果:

  • 在校准之前,所有模型都在白人患者中表现出比非白人患者更好的表现.
  • 后处理校准导致了各种改进,只有一些模型显示了增强的公平性能.
  • 该研究强调了在非多元数据集上训练的AI模型中固有的偏见.

结论:

关键词:
算法的公平性算法的公平性.乳腺癌 乳腺癌 乳腺癌深度学习是一种深度学习.均等的赔率使得赔率平等.提供平等的机会.后加工方法 后加工方法

更多相关视频

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

8.2K
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

相关实验视频

Last Updated: Jun 22, 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

2.7K
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

8.2K
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
  • 对于乳腺癌分期的深度学习模型可能会因为数据差异而使种族偏见永久化.
  • 后处理校准不是一个普遍有效的解决方案,以实现医疗AI的公平性.
  • 解决数据多样性对于开发公平的人工智能工具在乳腺癌护理方面至关重要.