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

Diagnostic Images for Mild Cognitive Impairment Are Sensitive to Alzheimer's Disease Biomarkers and Reveal Abnormal Scene Processing.

Journal of cognitive neuroscience·2026
Same author

Joint trajectories of brain atrophy, white matter hyperintensities and cognition quantify brain maintenance.

Nature communications·2026
Same author

A Modified Balanced Steady State Free Precession Sequence for Overhauser Magnetic Resonance Imaging.

Magnetic resonance in medicine·2026
Same author

Analysis and identification of volatile aroma compounds of the garlic-scented mushroom <i>Mycetinis scorodonius</i>.

Food chemistry: X·2026
Same author

Dysfunction of the episodic memory network in the Alzheimer's disease cascade.

Nature communications·2026
Same author

Coaxial Dipole Array With Switching Transmit Sensitivities for Ultrahigh Field MRI.

Magnetic resonance in medicine·2026

相关实验视频

Updated: May 28, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
06:03

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

411

灵活且具有成本效益的深度学习用于使用相循环bSSFP的加速多参数放松计.

Florian Birk1,2, Lucas Mahler3, Julius Steiglechner4,3

  • 1Department of Biomedical Magnetic Resonance, University of Tübingen, Tübingen, Germany. florian.birk@tuebingen.mpg.de.

Scientific reports
|February 9, 2025
PubMed
概括

深度神经网络 (DNN) 加快定量磁共振成像 (qMRI) 以更快,更准确的脑组织映射. 基于物理的DNN (PINN) 在多参数放松计中提供了更好的稳定性和一致性.

关键词:
深度神经网络 深度神经网络这是一个奇迹.多参数定量核磁共振成像有阶段循环的bSSFPFP放松计放松计放松计.

更多相关视频

In vivo Imaging of Biological Tissues with Combined Two-Photon Fluorescence and Stimulated Raman Scattering Microscopy
09:06

In vivo Imaging of Biological Tissues with Combined Two-Photon Fluorescence and Stimulated Raman Scattering Microscopy

Published on: December 20, 2021

3.2K
Author Spotlight: Enhancing Diagnostic Strategies and Biomarker Development for Comprehensive Lung Function Analysis
05:56

Author Spotlight: Enhancing Diagnostic Strategies and Biomarker Development for Comprehensive Lung Function Analysis

Published on: August 9, 2024

1.0K

相关实验视频

Last Updated: May 28, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
06:03

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

411
In vivo Imaging of Biological Tissues with Combined Two-Photon Fluorescence and Stimulated Raman Scattering Microscopy
09:06

In vivo Imaging of Biological Tissues with Combined Two-Photon Fluorescence and Stimulated Raman Scattering Microscopy

Published on: December 20, 2021

3.2K
Author Spotlight: Enhancing Diagnostic Strategies and Biomarker Development for Comprehensive Lung Function Analysis
05:56

Author Spotlight: Enhancing Diagnostic Strategies and Biomarker Development for Comprehensive Lung Function Analysis

Published on: August 9, 2024

1.0K

科学领域:

  • 医疗成像医学成像
  • 机器学习 机器学习
  • 神经科学是一个神经科学.

背景情况:

  • 定量磁共振成像 (qMRI) 的采用受到缓慢的获取和复杂的分析的阻碍.
  • 准确的参数映射对于qMRI的临床应用至关重要.
  • 开发高效和灵活的qMRI框架对于广泛的临床使用至关重要.

研究的目的:

  • 为了比较深度神经网络 (DNN) 和多参数 (MP) 放松计的代拟合框架,使用相循环平衡稳定状态自由前行 (pc-bSSFP) 成像.
  • 评估监督DNN (SVNN),物理信息DNN (PINN) 和MIRACLE in silico和in vivo的性能.
  • 评估DNN在加速数据采集和提高qMRI的稳定性方面的潜力.

主要方法:

  • 用于MP放松计的SVNN,PINN和MIRACLE框架的比较.
  • 在 silico 和 in vivo 评估中使用来自健康受试者的脑组织.
  • 蒙特卡洛采样用于噪声模拟和DNN培训,用于各种参数分布和信号噪声比.
  • 使用复杂值的MR数据用于基于DNN的加速.

主要成果:

  • 与SVNNs相比,PINNs在训练数据变异方面表现出更高的一致性和稳定性.
  • 通过利用复杂值的MR数据,DNN加速了数据采集的3倍.
  • 使用DNNs的全脑放松计是有效的,适应性的,并显示出低成本再培训的潜力.
  • 在 silico DNN 管道允许快速生成数据和培训,而不需要大量的字典或长时间的推断时间.

结论:

  • 基于DNN的MP-qMRI管道为定量成像提供了灵活和快速的方法.
  • 基于物理的DNN增强了qMRI参数映射的可靠性和适应性.
  • 这项工作突显了轻量级机器学习在加速临床采用qMRI方面的优势.