Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Effects of inulin-derived difructose anhydrides on DSS-induced colitis-associated behavioral alterations and gut microbiota-related responses in mice.

Food & function·2026

Same author

TP53 mutation-biased CD8<sup>+</sup> T cell exhaustion drives lethal outcome and therapy resistance in urothelial carcinoma.

British journal of cancer·2026

Same author

Time-resolved proteolipidomics of the human aorta identifies stage-specific lipid-protein modules across development and aging.

Cell reports·2026

Same author

[Modulatory effects of raw and honey-processed Astragali Radix fractions on intestinal microbiota, short-chain fatty acid metabolism and immune activity in rats with spleen deficiency].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026

Same author

Proliferative ecotype determines lethal prognosis and therapeutic benefit in urothelial carcinoma.

Cancer·2026

Same author

The metabolic change trajectory of skeletal muscle during the life cycle: arteriovenous metabolomics.

Life medicine·2026

Search research articles

相关实验视频

Updated: May 24, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

CGNet:用于无监督可变形图像注册的相关指导注册网络.

Yuan Chang, Zheng Li, Wenzheng Xu

IEEE transactions on medical imaging

|March 3, 2025

概括

这项研究引入了一种新的以相关性为指导的注册网络 (CGNet),用于可变形医疗图像的注册. CGNet 增强了特征匹配,以实现更准确,更有效的医疗图像对齐.

科学领域:

医学图像分析医学图像分析
深度学习 (Deep Learning) 是一种深度学习.
计算机视觉计算机视觉

背景情况:

可变形医疗图像的注册对于分析至关重要.
基于学习的方法提供了速度和竞争性性能.
现有的方法经常适应细分架构,忽视特征匹配.

研究的目的:

提出一个新的相关性引导注册网络 (CGNet),专门用于可变形医疗图像注册.
通过专注于明确特征匹配,提高医疗图像注册的准确性和效率.

主要方法:

开发了一种双流编码器,用于从移动和固定图像中独立提取特征.
引入了一个相关性学习模块,用于通过相关性图表明确匹配特征.
实现了粗到细的解码器,以生成变形子字段,以便准确地进行注册.

主要成果:

在三个评估指标上,CGNet取得了最先进的表现.
在实验中超过了12种现有的基于学习的注册方法.
在可变形的医疗图像注册中证明了卓越的准确性和效率.

结论:

更多相关视频

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

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

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

Published on: November 23, 2019

相关实验视频

Last Updated: May 24, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

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

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

Published on: November 23, 2019

拟议的CGNet有效地解决了当前基于深度学习的注册方法的局限性.
通过相关性图表明确的特征匹配是提高注册准确性的关键.
CGNet显示出在推进可变形医疗图像注册应用程序方面的巨大潜力.