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

Ultrasonography01:17

Ultrasonography

4.6K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
4.6K

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

Efficacy of ultrasound guidance for arteriovenous access cannulation in haemodialysis patients: a systematic review with quantitative synthesis.

BMC nephrology·2026
Same author

Ultrasound diagnosis of median nerve compression associated with an arterial variant at the elbow.

Medical ultrasonography·2026
Same author

Effectiveness of manual therapy, exercise, low-level laser therapy, ultrasound, and transcutaneous electrical nerve stimulation in reducing pain and improving mouth opening in temporomandibular joint disorders: A network meta-analysis of randomized controlled trials.

Medicine·2026
Same author

Response to the comment letter on 'Effectiveness of comprehensive geriatric assessment in frail older inpatients'.

Journal of the Formosan Medical Association = Taiwan yi zhi·2026
Same author

Unusual Sciatic Nerve Entrapment by the Inferior Gluteal Artery.

Diagnostics (Basel, Switzerland)·2026
Same author

Ultrasound-guided musculoskeletal interventions and professional boundaries: an international expert opinion.

European journal of physical and rehabilitation medicine·2026

相关实验视频

Updated: Jul 27, 2025

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography
06:09

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography

Published on: March 12, 2021

3.2K

深度学习算法用于预测部运动轨迹:动态肩膀超声波分析.

Yi-Chung Shu1, Yu-Cheng Lo1, Hsiao-Chi Chiu1

  • 1Institute of Applied Mechanics, College of Engineering, National Taiwan University, Taipei, Taiwan.

Ultrasonics
|June 8, 2023
PubMed
概括

一个新的深度学习算法在动态超声波中自动检测肩部的地标,提高了下部运动指标的准确性. 这项技术有助于更有效地识别异常的肩部运动模式.

关键词:
卷积神经网络是一个卷积神经网络.深度学习是一种深度学习.自我转移学习学习超声波学 超声波学 超声波学 超声波学在亚体内发生的冲击.

更多相关视频

A Novel Application of Musculoskeletal Ultrasound Imaging
10:53

A Novel Application of Musculoskeletal Ultrasound Imaging

Published on: September 17, 2013

24.2K
Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact
10:07

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Published on: February 10, 2015

19.3K

相关实验视频

Last Updated: Jul 27, 2025

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography
06:09

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography

Published on: March 12, 2021

3.2K
A Novel Application of Musculoskeletal Ultrasound Imaging
10:53

A Novel Application of Musculoskeletal Ultrasound Imaging

Published on: September 17, 2013

24.2K
Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact
10:07

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Published on: February 10, 2015

19.3K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 整形外科 整形外科 整形外科

背景情况:

  • 动态肩部超声波测试对于评估下运动和识别肩部病理非常有价值.
  • 在超声波中手动识别地标是劳动密集型和耗时的.

研究的目的:

  • 评估深度学习算法的可行性,用于从动态肩膀超声波中自动提取亚体运动度量.
  • 为了比较不同深度学习模型与手动测量的准确性.

主要方法:

  • 开发了一个深度学习框架,包括卷积神经网络 (CNN) 和基于自转移学习的CNN (STL-CNN) 带有或没有自动编码器 (AE).
  • 该算法跟踪了17名参与者在肩膀绑架/引送过程中较大的结核相对于侧侧的轨迹.
  • 算法输出和手动地标标签 (地面真相) 之间的平均绝对误差 (MAE) 是主要的结果指标.

主要成果:

  • 在STL-CNN模型 (带有或没有AE) 中,水平地标差异的MAE明显低于标准CNN.
  • 与CNN相比,STL-CNN还显示了与CNN相比,垂直地标本地化准确度的提高.
  • 作为关键指标的最小垂直角角距离,STL-CNN与CNN (0.081-0.333厘米) 的误差明显较低 (0.002-0.007厘米).

结论:

  • 一种深度学习算法,特别是STL-CNN,可以在动态肩膀超声波中自动检测关键解剖标志.
  • 开发的框架准确地捕捉到最小的垂直形形距离,这对于临床评估形下运动至关重要.
  • 这种自动化方法为在临床实践中分析肩膀生物力学提供了更有效,更准确的方法.