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

Reliable Uncertainty Estimation via Discriminative Feature Learning for Evidential Deep Classification.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Targeted Inhibition of Bacterial Repair by Nitrite-Derived Reactive Nitrogen Species Improves UVC Disinfection Efficiency.

Environmental science & technology·2026
Same author

Repeated low-level red light therapy for pathologic myopia: a case series of two adult patients.

The British journal of ophthalmology·2026
Same author

Synergistic adaptation of rice root phosphorus uptake kinetics and leaf carbon-nitrogen metabolism under low-phosphorus conditions.

Frontiers in plant science·2026
Same author

Risk factors for intraoperative floppy iris syndrome in female cataract patients: The roles of ARB medication and diabetes mellitus.

Advances in ophthalmology practice and research·2026
Same author

Intraocular lens power calculation in highly myopic eyes with axial length ≥ 28 mm: Impact of two corneal keratometries and anterior segment parameters.

Acta ophthalmologica·2026

相关实验视频

Updated: May 24, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

348

SFM-Net:基于语义特征的多阶段网络,用于无监督图像注册.

Tai Ma, Xinru Dai, Suwei Zhang

    IEEE journal of biomedical and health informatics
    |March 3, 2025
    PubMed
    概括

    SFM-Net是一个无监督的语义特征网络,可以改善复杂结构的医疗图像注册. 它通过使用新的双流U-Net和多尺度变形场来对准语义区域来实现准确和不同形态的结果.

    科学领域:

    • 医疗成像医学成像
    • 计算机视觉 计算机视觉
    • 生物医学工程 生物医学工程

    背景情况:

    • 对复杂的解剖结构的医学图像进行准确的记录对于一般方法来说是具有挑战性的.
    • 现有的深度学习方法通常由于向下采样的特征提取而难以实现细对应.

    研究的目的:

    • 介绍SFM-Net,一个无监督的多阶段语义特征网络,用于改进医疗图像注册.
    • 在复杂的解剖结构中增强语义相关区域的对齐.

    主要方法:

    • 开发了SFM-Net,这是一个无监督的网络,具有两阶段的培训策略:强度图像注册和语义特征注册.
    • 使用双流特征提取模块 (DFEM) 使用U-Net结构来捕获语义信息.
    • 引入了一种精制的变形场生成模块 (RDGM),用于在单一网络中进行粗到细的多尺度注册.

    主要成果:

    • SFM-Net在3D脑部MRI和肝脏CT数据集上实现了准确和不同形态的注册.
    • 与最先进的注册技术相比,提出的方法显示出更高的性能.
    • 语义特征注册有效地改善了复杂解剖结构的对齐.

    结论:

    更多相关视频

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    451
    Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
    02:09

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

    Published on: April 12, 2024

    519

    相关实验视频

    Last Updated: May 24, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    348
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    451
    Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
    02:09

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

    Published on: April 12, 2024

    519
  • SFM-Net提供了一个强大的解决方案,用于无监督的医疗图像记录,特别是复杂的解剖区域.
  • 该网络的基于特征的语义方法和双阶段培训提高了注册准确性和结构调整.
  • 这种方法通过提供更精确的注册工具,推进了医疗图像分析领域.