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

Routine admission biomarkers for identifying co-infection and stratifying severity in pediatric macrolide-resistant <i>Mycoplasma pneumoniae</i> pneumonia: a retrospective cohort study.

Translational pediatrics·2026
Same author

Regulatory Effects of the PDE8B Inhibitor PF-04957325 on Cognitive Impairment and Neuroinflammation in Aβ-Induced Alzheimer's Disease Mouse Models.

Neurochemical research·2026
Same author

The "DeepSeek effect" and the adoption-integration gap of generative artificial intelligence in clinical practice: a national online convenience cross-sectional survey of academic critical care physicians in China.

Frontiers in medicine·2026
Same author

A self-attention-based deep learning model for identifying key genes in insect pupal metamorphosis.

BMC genomics·2026
Same author

Cancer Heterogeneity and Cancer Cell Plasticity: Molecular Mechanisms and Precision Therapy.

MedComm·2026
Same author

Effect of Tongxie Yaofang formula on the gut microbiota of diarrhea model mice: a combined strategy of network pharmacology, molecular docking, and 16S rRNA gene sequencing.

Bioscience of microbiota, food and health·2026

相关实验视频

Updated: Jul 19, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

544

一种两步深度学习方法,用于3DCT-2DUS在呼吸过程中进行脏注册.

Yanling Chi1, Yuyu Xu2, Huiying Liu3

  • 1Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way #21-01 Connexis South, Singapore, 138632, Republic of Singapore. chiyl@i2r.a-star.edu.sg.

Scientific reports
|August 8, 2023
PubMed
概括

脏RegNet是一个新的深度学习管道,用于在自由呼吸期间注册3DCT和2D超声波脏图像. 这种方法可以实现精确的脏注册,这对于医学成像应用至关重要.

更多相关视频

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

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

Published on: November 23, 2019

8.0K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

406

相关实验视频

Last Updated: Jul 19, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

544
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

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

Published on: November 23, 2019

8.0K
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

406

科学领域:

  • 医疗成像医学成像
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 计算解剖学的计算解剖学

背景情况:

  • 由于呼吸运动,在3DCT和2D超声波之间准确地注册脏是具有挑战性的.
  • 现有的方法可能会在不同的成像方式和分辨率之间的语义差距上扎.

研究的目的:

  • 开发和验证KidneyRegNet,3DCT和2D超声波脏扫描的新型深度注册管道.
  • 通过使用先进的网络架构和训练策略,解决3D CT-2D US在自由呼吸过程中注册的困难.

主要方法:

  • 提出 KidneyRegNet,一个管道,包括一个手工制作的纹理特征网络和一个3D-2D CNN注册网络.
  • 在编码器-解码器结构中使用特征图像-运动 (FIM) 损失来进行等级回归.
  • 使用无监督的一次循环转移学习,在预训练后适应患者特定数据.

主要成果:

  • 实现了CT-US脏注册的平均轮距离 (MCD) 为0.94mm,CT-CT注册的平均轮距离为1.15mm.
  • 在不同的转换大小中表现出强大的性能,CT-US的MCD为0.82-1.10毫米,CT-CT为1.02-1.28毫米.
  • 在各种数据集上得到验证,包括132个US序列,39个多相CT,210个单相CT和25个CT-US对.

结论:

  • 脏RegNet有效地解决了在自由呼吸条件下3D CT-2D US脏注册的复杂性.
  • 新的网络结构和转移学习策略提高了注册准确性和在临床环境中的适用性.
  • 这条管道为改善医学成像中的非刚性注册提供了一个有希望的解决方案.