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

Hearing01:31

Hearing

52.2K
When we hear a sound, our nervous system is detecting sound waves—pressure waves of mechanical energy traveling through a medium. The frequency of the wave is perceived as pitch, while the amplitude is perceived as loudness.
52.2K

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

Glymphatic System Dysfunction Associated with Inflammatory Factors in Asymptomatic Neurosyphilis.

Current medical imaging·2026
Same author

Multilayer network analysis of dynamic network reconfiguration in age-related hearing loss: a cross-sectional case-control study.

Quantitative imaging in medicine and surgery·2025
Same author

Effect of hearing ability on inflammation and glymphatic function affecting cognition in older adults.

GeroScience·2025
Same author

Predominant white matter microstructural changes over gray matter in tinnitus brain.

NeuroImage·2025
Same author

Neurovascular coupling dysfunction associated with inflammatory factors in sudden sensorineural hearing loss.

Neuroscience·2025
Same author

Impaired network organization in mild age-related hearing loss.

MedComm·2025

相关实验视频

Updated: Jul 1, 2025

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training
07:05

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

Published on: August 24, 2017

11.0K

基于静止状态功能连接的耳声分类,使用卷积神经网络架构.

Qianhui Xu1, Lei-Lei Zhou2, Chunhua Xing2

  • 1Department of Otolaryngology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, 107 West Yanjiang Road, Guangzhou, Guangdong Province 510120, China.

NeuroImage
|March 11, 2024
PubMed
概括
此摘要是机器生成的。

一个新的卷积神经网络 (CNN) 模型有效地使用静止状态功能性MRI (rs-fMRI) 功能连接 (FC) 诊断主观耳. 这项研究证实了rs-fMRI FC的存在.

关键词:
卷积神经网络是一种卷积神经网络.功能连接性的功能连接性.休息状态的fMRI.声 (Tinnitus) 是一种听力障碍.

更多相关视频

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.1K
Functional Imaging of Auditory Cortex in Adult Cats using High-field fMRI
10:50

Functional Imaging of Auditory Cortex in Adult Cats using High-field fMRI

Published on: February 19, 2014

11.6K

相关实验视频

Last Updated: Jul 1, 2025

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training
07:05

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

Published on: August 24, 2017

11.0K
Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

18.1K
Functional Imaging of Auditory Cortex in Adult Cats using High-field fMRI
10:50

Functional Imaging of Auditory Cortex in Adult Cats using High-field fMRI

Published on: February 19, 2014

11.6K

科学领域:

  • 神经成像是一种神经成像.
  • 机器学习 机器学习
  • 医学诊断 医学诊断 医学诊断

背景情况:

  • 主观耳患者的异常功能连接 (FC) 已被广泛使用休息状态功能MRI (rs-fMRI) 研究.
  • rs-fMRI FC作为 tinnitus 的生物标志物的诊断疗效仍然没有得到验证.
  • 开发主观耳的客观诊断工具对于临床实践至关重要.

研究的目的:

  • 建立一个卷积神经网络 (CNN) 模型,以区分耳患者与健康对照者,基于rs-fMRI FC.
  • 评估rs-fMRI FC作为主观耳的成像标记物的诊断价值.
  • 为主观耳的临床诊断提供指导和快速诊断工具.

主要方法:

  • 在100名耳患者和100名健康对照者的rs-fMRI数据上训练了一名CNN模型.
  • 在CNN架构中使用了一个不对称的卷积层.
  • 将CNN模型与传统的机器学习和转移学习模型进行了比较,所有模型都在三个不同的大脑地图上进行了测试.

主要成果:

  • 与传统和转移学习模型相比,CNN模型表现出优异的性能,在Dos_160地图上实现了曲线下的最高面积 (AUC = 0.944).
  • 性能最好的模型确定了默认模式网络,突出网络和感觉运动网络在区分耳患者与对照者的过程中至关重要.
  • 结果突出了特定大脑网络在主观耳的客观诊断中的潜力.

结论:

  • 开发的CNN模型使用rs-fMRI数据准确诊断耳患者.
  • 这项研究证实了rs-fMRI测量的主观耳的功能连接的诊断价值.
  • 这些发现支持使用rs-fMRI FC和CNN作为潜在的临床诊断工具.