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 author

3D and 4D Free-Breathing Abdominal T1-Weighted MRI in Clinical Practice Using Deep Learning Auto-Navigation and Reconstruction.

Magnetic resonance in medicine·2026
Same author

Impact of Baydur Ratio Correction on the Reliability of Esophageal Pressure Measurement.

Journal of applied physiology (Bethesda, Md. : 1985)·2026
Same author

Sex-related differences in lung injury distribution and outcomes in COVID-19 acute respiratory failure: insights from the CT-COVID19 multicenter study group.

Intensive care medicine experimental·2026
Same author

Association of "Emptying Emphysema" with Clinical and Radiographic Features in People with Smoking History.

Annals of the American Thoracic Society·2026
Same author

Incorporating Dental Anatomy Into MRI-Based Vocal Tract Models Using Zero Echo Time Imaging.

Journal of voice : official journal of the Voice Foundation·2026
Same author

A Contemporary Review of Operative Indications for Chest Wall Trauma.

Thoracic surgery clinics·2026

相关实验视频

Updated: May 24, 2025

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

20.2K

开源手动注释声道数据库用于使用深度学习从3DMRI进行自动细分:比较2D和3D卷积和变压器网络:深度学习:比较2D和3D卷积和变压器网络

Subin Erattakulangara1, Karthika Kelat1, Katie Burnham2

  • 1Roy J. Carver Department of Biomedical Engineering, University of Iowa, Iowa City, Iowa.

Journal of voice : official journal of the Voice Foundation
|March 6, 2025
PubMed
概括

深度学习模型,特别是带有转移学习的3D U-Net,显示了来自3D MRI的自动声道细分的前景,提高了语音和语音研究的效率和准确性.

关键词:
深度学习是一种深度学习.这就是为什么MRI是MRI.开源注释数据库是一个开源的注释数据库.分段化 分段化 分段化 分段化语音通道的声音

更多相关视频

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
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

2.6K

相关实验视频

Last Updated: May 24, 2025

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures
12:30

A Comprehensive Protocol for Manual Segmentation of the Medial Temporal Lobe Structures

Published on: July 2, 2014

20.2K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
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

2.6K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 语音科学 语言科学

背景情况:

  • 精确的声道细分从3DMRI对于声音,言语和歌唱应用至关重要.
  • 手动细分是耗时且容易出现错误的,需要自动化解决方案.

研究的目的:

  • 从3DMRI数据评估深度学习算法对自动声道细分的有效性.
  • 为了比较不同深度学习架构在声道细分方面的性能.

主要方法:

  • 评估了四种深度学习架构:2D切片式U-Net,3D U-Net,3D U-Net与转移学习,3D变压器U-Net (3D U-NetR).
  • 使用了来自10名法语发言者的53个声道卷的数据集,手动注释作为参考细分.
  • 性能被评估使用子系数,豪斯多夫距离和结构相似度指数.

主要成果:

  • 3D U-Net和3D U-Net与转移学习实现了最高的子系数 (0.896).
  • 转移学习模型的性能与3D U-Net相比,使用的训练数据较少,Hausdorff距离的变化较低.
  • 所有模型都在与特定的声音 (如 /kõn/) 和骨区域附近的细分扎;然而,口腔喉和喉喉空间通常被准确地细分.

结论:

  • 3D卷积网络,特别是具有转移学习的3D卷积网络,对于3DMRI的自动声道细分是有效的.
  • 未来的研究应该旨在改善具有挑战性的声道配置和边界划分的细分.