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

De novo contralateral vertebral artery dissection after treatment: incidence and clinical characteristics.

Acta neurochirurgica·2026
Same author

Effect of Carnosine Supplementation on Warmed-Over Flavor, Volatile Compounds, and Meat Quality in Ground Chicken Breast and Thigh Meat.

The journal of poultry science·2026
Same author

A case of coexistence of spinal intradural capillary hemangioma and craniocervical junction dural arteriovenous fistula.

Acta neurologica Belgica·2026
Same author

Fundamental characterization of surface temperature effects on ExacTrac Dynamic monitoring accuracy: A phantom study.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same author

Denoising preclinical MRI with vendor-neutral deep learning-based image reconstruction.

Journal of neuroscience methods·2026
Same author

Deep learning reconstruction for liver DWI: impact on image quality and ADC quantification.

European journal of radiology·2026

相关实验视频

Updated: Jul 7, 2025

Magnetic Resonance Imaging Quantification of Pulmonary Perfusion using Calibrated Arterial Spin Labeling
12:29

Magnetic Resonance Imaging Quantification of Pulmonary Perfusion using Calibrated Arterial Spin Labeling

Published on: May 30, 2011

13.7K

训练数据条件对动脉旋转标记参数估计的影响,使用基于模拟的监督深度神经网络.

Shota Ishida1, Makoto Isozaki2, Yasuhiro Fujiwara3

  • 1From the Department of Radiological Technology, Faculty of medical sciences, Kyoto College of Medical Science, Kyoto.

Journal of computer assisted tomography
|December 27, 2023
PubMed
概括

优化训练数据的地面真实范围可显著提高深度神经网络 (DNN) 在估计脑血流 (CBF) 和动脉传输时间 (ATT) 的准确性. 适当的设置可确保从动脉旋转标记信号中获得准确和可靠的估计.

更多相关视频

Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders
05:23

Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders

Published on: May 31, 2024

570
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.7K

相关实验视频

Last Updated: Jul 7, 2025

Magnetic Resonance Imaging Quantification of Pulmonary Perfusion using Calibrated Arterial Spin Labeling
12:29

Magnetic Resonance Imaging Quantification of Pulmonary Perfusion using Calibrated Arterial Spin Labeling

Published on: May 30, 2011

13.7K
Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders
05:23

Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders

Published on: May 31, 2024

570
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.7K

科学领域:

  • 神经成像是一种神经成像.
  • 医学物理 医学物理
  • 人工智能的人工智能

背景情况:

  • 深度神经网络 (DNN) 显示出从动脉旋转标记 (ASL) 信号中估计大脑血流 (CBF) 和动脉传输时间 (ATT) 的前景.
  • 这些DNN的准确性在很大程度上取决于训练数据集的特点,特别是使用的地面真相 (GT) 范围.

研究的目的:

  • 调查CBF和ATT的地面真相 (GT) 范围对基于模拟的监督DNN的性能的影响.
  • 确定训练数据的最佳GT范围,以提高ASL信号分析的准确性和可靠性.

主要方法:

  • 经过训练的DNN使用来自ASL信号模拟的36个不同的训练数据模式.
  • 使用模拟测试数据 (1,000,000分) 和来自健康志愿者和莫亚莫亚患者的体内数据评估了DNN性能.
  • 使用NMAE,NRMSE和CV Net等指标评估准确性,精度和噪声免疫力.

主要成果:

  • 达到了最高的DNN性能,GT范围为CBF的0-120mL/100g/min,ATT的0-4500ms.
  • 虽然预测的CBF和ATT值随着GT范围的变化而变化,但适当的设置保持了DNN准确性,精度和噪声免疫力.
  • 这些发现在模拟和体内研究中都是一致的.

结论:

  • 对于训练数据的GT范围的选择对基于模拟的监督DNN用于ASL分析的性能产生了关键影响.
  • 适当的GT范围设置对于实现CBF和ATT的准确和精确估计至关重要,而不适当的设置可能会降低性能.