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

Genetic variation of human papillomavirus type 39 E6 and E7 genes in central China.

Virology journal·2026
Same author

Generating synthetic CT from MR images for radiation-free computer-assisted quantification of hip morphology.

European journal of radiology·2026
Same author

A case of synchronous double primary combined hepatocellular-cholangiocarcinoma complicated with gallbladder adenocarcinoma: a rare case report.

Frontiers in oncology·2026
Same author

CIM-VTP: Correlation-Guided Image Modeling With Visual-Textual Task Prompt for Universal Medical Image Registration.

IEEE transactions on medical imaging·2026
Same author

TPDPM: Text promptable diffusion probabilistic model for referring surgical instrument segmentation.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

Primary extranodal marginal zone non-hodgkin lymphoma of the prostate: a case report.

Frontiers in oncology·2026

相关实验视频

Updated: Jul 6, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

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

Published on: October 27, 2023

1.2K

微笑:罗语 多尺度 交互式表示 学习层次差异形态可变形图像注册学习

Xiaoru Gao1, Guoyan Zheng1

  • 1Institute of Medical Robotics, School of Biomedical Engineering, 800 DongChuan Road, Shanghai Jiao Tong University, Shanghai, 200240, China.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
|December 29, 2023
PubMed
概括

这项研究引入了一种新的深度学习方法,用于可变形医疗图像的注册,提高精度和保存图像拓. 该方法增强了信件匹配,并有效地处理大空间位移.

关键词:
深度学习是一种深度学习.可变形图像的注册方式不同形态变形的变形.代表性的学习学习.

更多相关视频

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K
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

612

相关实验视频

Last Updated: Jul 6, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

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

Published on: October 27, 2023

1.2K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K
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

612

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 可变形医疗图像的注册对于临床应用至关重要,它可以实现图像之间的点对应.
  • 无监督深度学习方法提供快速推断,但在特征对应,处理大位移和保存转换属性方面存在局限性.
  • 现有的方法往往忽略了明确的特征对应模型和可取的属性,如拓保存和可逆性.

研究的目的:

  • 提出一种新的卷积神经网络 (CNN),用于无监督的可变形医疗图像注册.
  • 解决现有方法的局限性,包括被忽视的特征对应性,在大位移上有限的性能,以及被忽视的拓保存和可逆性.
  • 开发一种方法,在确保理想的转换性质的同时,实现高登记精度.

主要方法:

  • 一个新的CNN架构,采用语多尺度交互表示学习 (SMILE) 编码器和层次差异形态变形 (HDD) 解码器.
  • 微笑编码器专注于学习有效的特征表示和建立空间对应.
  • 硬盘解码器以层次的形式回归密集的变形场 (从粗到细),并结合了局部可逆损失 (LIL) 进行拓保存和局部可逆性.

主要成果:

  • 与最先进的方法相比,拟议的方法在两个公共脑图像数据集上表现出更高的性能.
  • 在Neurite-OASIS数据集上获得了0.815的平均子相似系数 (DSC) 和0.633毫米的平均表面距离 (ASSD).
  • 该方法有效地解决了特征对应的局限性,大空间位移,并确保拓保存和可逆性.

结论:

  • 新型CNN与SMILE编码器和HDD解码器显著推进了无监督可变形医疗图像的注册.
  • 拟议的局部可逆损失 (LIL) 有效地促进拓保存和局部可逆性,而不会影响准确性.
  • 该方法显示了各种临床应用的巨大潜力,需要准确可靠的图像记录.