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

The role of diffusion-weighted MRI in biological image-guided radiation therapy: a roadmap.

Physics in medicine and biology·2026
Same author

A Bimetallic Nanozyme with Cascade Effect for Synergistic Therapy of Cancer.

ChemMedChem·2022
Same author

JAK2/STAT3 inhibition attenuates intestinal ischemia-reperfusion injury via promoting autophagy: in vitro and in vivo study.

Molecular biology reports·2022
Same author

Tunable Crosslinking, Reversible Phase Transition, and 3D Printing of Hyaluronic Acid Hydrogels via Dynamic Coordination of Innate Carboxyl Groups and Metallic Ions.

ACS applied bio materials·2022
Same author

CircCCNB1 silencing acting as a miR-106b-5p sponge inhibited GPM6A expression to promote HCC progression by enhancing DYNC1I1 expression and activating the AKT/ERK signaling pathway.

International journal of biological sciences·2022
Same author

Gingival mesenchymal stem cell-derived exosomes are immunosuppressive in preventing collagen-induced arthritis.

Journal of cellular and molecular medicine·2021

相关实验视频

Updated: Jan 14, 2026

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning
10:25

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

2.3K

在基于深度学习的瘤微结构参数映射中平衡偏差和差异.

Jiaren Zou1, Yue Cao1,2,3

  • 1Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan, USA.

Magnetic resonance in medicine
|October 23, 2025
PubMed
概括

新的B2V-Net平衡了扩散MRI分析中的偏差和差异,改善了瘤微结构参数量化,与现有方法相比,可以更好地诊断和预后.

关键词:
深度学习是一种深度学习.扩散磁力共振成像 (MRI) 扩散头部和部癌症 头部和部癌症模型配件 模型配件组织微观结构组织微观结构.

更多相关视频

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.6K
Author Spotlight: Creating Human Vascularized Micro-Tumors as Models for Translational Cancer Research
07:26

Author Spotlight: Creating Human Vascularized Micro-Tumors as Models for Translational Cancer Research

Published on: September 15, 2023

2.4K

相关实验视频

Last Updated: Jan 14, 2026

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning
10:25

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

2.3K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.6K
Author Spotlight: Creating Human Vascularized Micro-Tumors as Models for Translational Cancer Research
07:26

Author Spotlight: Creating Human Vascularized Micro-Tumors as Models for Translational Cancer Research

Published on: September 15, 2023

2.4K

科学领域:

  • 生物医学成像技术 生物医学成像技术
  • 机器学习在医学成像中的应用
  • 量化MRI是指数量化的MRI.

背景情况:

  • 时间依赖的扩散MRI对于瘤微结构参数量化至关重要.
  • 目前的方法,如非线性最小平方匹配 (NLLS) 和平均平方误差深度学习 (MSE-Net),具有偏差差异权衡的挑战.
  • NLLS提供低偏差但高偏差,而MSE-Net提供低偏差但高偏差.

研究的目的:

  • 研究NLLS和MSE-Net在扩散MRI模型适配中的偏差-变异特征.
  • 提出一种用于控制定量MRI中偏差差异权衡的新方法.
  • 为了提高瘤微结构参数估计的准确性和可靠性.

主要方法:

  • 在贝叶斯框架内对NLLS和MSE-Net进行了改革,以了解偏差差异行为.
  • 推出了B2V-Net,一种监督学习方法,具有可调节的偏差差异加权损失函数.
  • 评估了B2V-Net与NLLS和MSE-Net相比,使用各种参数和噪声水平的数值模拟,以及头癌患者的体内模拟.

主要成果:

  • 在贝叶斯分析中通过平面后部分布解释了NLLS和MSE-Net行为.
  • B2V-Net成功控制了偏差差异权衡,将标准偏差减少了56%与NLLS相比.
  • 与MSE-Net相比,B2V-Net实现了18%的偏差降低,体内参数图显示出平衡的流性和准确性.

结论:

  • 展示并解释了NLLS和MSE-Net中固有的偏差差异问题.
  • 拟议的B2V-Net有效地平衡了扩散MRI分析中的偏差和差异.
  • 这项工作为设计针对特定临床成像应用的定制损失函数提供了有价值的见解和方法.