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

Early Knee Osteoarthritis Detection by Multi-Component T<sub>2</sub> Mapping.

Bioengineering (Basel, Switzerland)·2026
Same author

Adiabatic Pulse Shape Influence on the Orientation Dependence of T<sub>1ρ</sub> Relaxation.

Magnetic resonance in medicine·2026
Same author

Detection of Early Knee Osteoarthritis Using Multi-Component T<sub>1ρ</sub> Mapping.

Journal of magnetic resonance imaging : JMRI·2025
Same author

Feasibility of a UTE Stack-of-Spirals Sequence for T<sub>1ρ</sub> Mapping of Achilles Tendinopathy.

NMR in biomedicine·2025
Same author

HSGDNet: Hybrid Synthetic-Data-Guided Deep Learning With NLS Refinement for Fast Multi-Component T1ρ Knee Mapping.

NMR in biomedicine·2025
Same author

Feasibility of a UTE Stack-of-Spirals Sequence for Biexponential T<sub>1ρ</sub> Mapping of Whole Knee Joint.

NMR in biomedicine·2025

相关实验视频

Updated: May 10, 2025

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis
06:31

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis

Published on: October 6, 2023

1.9K

用MR指纹进行定量膝关节映射的微调深度学习模型及其与字典匹配方法的比较:微调定量MRF深度学习模型.

Xiaoxia Zhang1, Hector L de Moura1, Anmol Monga1

  • 1Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA.

NMR in biomedicine
|April 22, 2025
PubMed
概括

用于磁共振指纹 (MRF) 的微调神经网络 (NN) 提高了定量绘图的准确性. 优化的NN提供了一个强大的替代词典匹配用于分析膝关节软骨组成.

关键词:
在MR指纹采集.深度学习是一种深度学习.肌肉骨成像系统成像定量的MRI是指MRI的数量.

更多相关视频

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

2.9K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

7.8K

相关实验视频

Last Updated: May 10, 2025

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis
06:31

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis

Published on: October 6, 2023

1.9K
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

2.9K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

7.8K

科学领域:

  • 生物医学成像技术 生物医学成像技术
  • 人工智能在医学中的应用
  • 量化MRI是指数量化的MRI.

背景情况:

  • 磁共振指纹 (MRF) 能够同时,非侵入性量化多个MRI参数,以检测骨关节炎相关的软骨变化.
  • 深度学习 (DL) 方法为MRF量化提供了比传统的字典匹配 (DM) 计算优势,但需要仔细微调.
  • 有限的研究重点是优化神经网络 (NN) 训练参数,并比较DL与DM在MRF中的性能.

研究的目的:

  • 调查训练参数选择对MRF中NN性能的影响.
  • 为了比较微调的NN的性能与字典匹配 (DM) 方法用于MRF的多参数映射.
  • 用合成,幻影和体内数据评估基于NN的MRF量化的准确性和稳定性.

主要方法:

  • 对NN超参数的优化和对MRF数据的奇数值分解 (SVD) 组件的探索.
  • 改进了用于比较分析的词典匹配 (DM) 方法.
  • 实验验证使用合成数据集,NIST/ISMRMMMRI系统幻影和体内健康志愿者的膝盖MRF数据进行实验验证.

主要成果:

  • 培训参数的选择极大地影响了NN在MRF量化中的表现.
  • 与合成数据集上的DM相比,NN对T1,T2和T1ρ映射的准确性和稳定性得到了改进.
  • 在体内结果显示,与DM相比,NN的T1比较,T2略低,T1ρ测量略高.

结论:

  • 微调的NN对于提高MRF多参数定量映射的准确性和稳定性至关重要.
  • 基于NN的方法为分析膝关节MRF数据提供了有希望的进步.
  • 这项研究强调了严格的NN优化对于可靠的定量MRI的重要性.