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

Prosopagnosia01:24

Prosopagnosia

1.3K
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
1.3K

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

Non-Classical Monocyte Expansion Is Independently Associated with Anemia Severity in Patients with ESKD: The Immunity in End-Stage Renal Disease Cohort-Study.

Kidney360·2026
Same author

Aging-associated immune signature as a predictor of mortality in end-stage renal disease: results from the longitudinal iESRD study.

Immunity & ageing : I & A·2025
Same author

Anti-herpetic treatment reduces dementia risk: A systematic review and meta-analysis.

Journal of Alzheimer's disease : JAD·2025
Same author

Clinical Manifestations.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Relationship between amyloid burden, cholinergic integrity, and cognitive function.

Journal of Alzheimer's disease : JAD·2025
Same author

Matrix metalloproteinases and tissue inhibitors of metalloproteinases as the biomarkers of Alzheimer's disease: A meta-analysis.

Brain research·2025

相关实验视频

Updated: May 2, 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

7.5K

基于多流卷积神经网络的轻度认知障碍预测.

Chien-Cheng Lee1, Hong-Han Hank Chau2, Hsiao-Lun Wang2

  • 1Department of Electrical Engineering, Yuan Ze University, Taoyuan, 320, Taiwan. cclee@saturn.yzu.edu.tw.

BMC bioinformatics
|September 12, 2024
PubMed
概括

这项研究引入了一个多流卷积神经网络 (MCNN) 来从面部视频中检测轻度认知障碍 (MCI). 该MCNN模型在参与者层面识别MCI时实现了100%的准确性,提供了一种非侵入性查方法.

关键词:
在美国,CNN是CNN.深度学习是一种深度学习.面部特征 面部特征 面部特征在MCI中,MCI是MCI.这就是ResNet ResNet.

更多相关视频

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

2.9K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

983

相关实验视频

Last Updated: May 2, 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

7.5K
Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

2.9K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

983

科学领域:

  • 人工智能的人工智能
  • 机器学习 机器学习
  • 医学诊断 医学诊断 医学诊断

背景情况:

  • 轻度认知障碍 (MCI) 是正常衰老和痴呆之间的过渡阶段.
  • 早期MCI诊断对于有效的医疗干预至关重要.
  • 目前的诊断方法,包括认知和神经成像测试,往往是昂贵和耗时的.

研究的目的:

  • 开发和评估一种新的多流卷积神经网络 (MCNN) 模型,用于使用面部视频预测MCI.
  • 探索面部数据作为MCI检测的非侵入性生物标志物的潜力.
  • 建立一种自动化,成本效益高,客观的MCI查方法.

主要方法:

  • 使用了来自45名参与者的48个面部视频数据集 (35个正常,13个MCI).
  • 采用多流卷积神经网络 (MCNN) 来从视频段中提取空间和动态面部特征.
  • 评估了27个MCNN模型组合,不同的ResNet架构,优化器和激活功能.

主要成果:

  • 在使用ResNet-50,Swish激活和Ranger优化器的细分级别上,MCNN模型实现了89%的F1得分.
  • 与Swish和Ranger一起的ResNet-18骨干在参与者层面上实现了完美的100%F1得分.
  • ResNet-50在不同的优化器中表现出稳定性,表明对超参数调整的稳定性.

结论:

  • 面部视频可以有效地用于预测MCI,作为一个有价值的生物标志物.
  • 开发的MCNN方法为传统的MCI查方法提供了一个有希望的,自动化的,非侵入性的和廉价的替代方案.
  • 该研究提供了对超参数优化的见解,以提高使用面部数据的MCI预测准确度.