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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

6.9K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
6.9K

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

Cardiovascular magnetic resonance imaging and spectroscopy in clinical long-COVID-19 syndrome: a prospective case-control study.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2022
Same author

Correlation between the neutrophil-to-lymphocyte ratio and clinicopathological parameters in epithelial ovarian cancer patients and its effect on prognosis-a retrospective cohort study.

Gland surgery·2022
Same author

CircRNA RNF10 inhibits tumorigenicity by targeting miR-942-5p/GOLIM4 axis in breast cancer.

Environmental and molecular mutagenesis·2022
Same author

Improving the gel properties of duck egg white by synergetic phosphorylation/ultrasound: Gel properties, crystalline structures, and protein structure.

Ultrasonics sonochemistry·2022
Same author

Peimine-induced apoptosis and inhibition of migration by regulating reactive oxygen species-mediated MAPK/STAT3/NF-κB and Wnt/β-catenin signaling pathways in gastric cancer MKN-45 cells.

Drug development research·2022
Same author

Analysis of CMTM6 and CMTM4 expression as potential regulators of the PD-L1 protein and its association with prognosis in glioma cancer.

Acta biochimica et biophysica Sinica·2022

相关实验视频

Updated: Sep 12, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K

用于医疗图像记录的反复推断机器.

Yi Zhang1, Yidong Zhao1, Hui Xue2

  • 1Delft University of Technology, Department of Imaging Physics, Delft, The Netherlands.

Medical image analysis
|August 8, 2025
PubMed
概括

循环推断图像注册 (RIIR) 网络提高了医疗图像注册的准确性和数据效率. 这种新的深度学习方法即使在训练数据有限的情况下也能实现卓越的性能,优于现有的方法.

关键词:
图像的注册 图像的注册超级学习 (Meta learning) 是一种超级学习.循环推断机器是一个反复推断机器.

更多相关视频

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

1.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

相关实验视频

Last Updated: Sep 12, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.4K
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

1.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算生物学 计算生物学

背景情况:

  • 医疗图像注册对齐voxels跨多个图像进行分析.
  • 深度学习方法提供了速度,但可以牺牲准确性,并要求大数据集.
  • 基于优化的方法不需要培训,但可能更慢.

研究的目的:

  • 开发一种新的,数据效率高的深度学习方法,用于医疗图像注册.
  • 提高注册准确性和培训数据效率.
  • 解决现有的深度学习和基于优化的注册技术的局限性.

主要方法:

  • 提出了反复推断图像注册 (RIIR) 网络,一个元学习的解决方案.
  • 制定注册作为一个代过程学习优化优化更新规则.
  • 集成隐式规范化与显式梯度输入.

主要成果:

  • 在脑MRI,肺CT和心脏MRI数据集中,RIIR展示了卓越的注册准确性和高数据效率.
  • 与其他深度学习方法相比,仅使用5%的训练数据实现了最先进的性能.
  • 废除研究证实了隐藏状态在循环推理框架中的重要贡献.

结论:

  • 该RIIR网络提供了一个高效的数据框架,用于基于深度学习的医疗图像注册.
  • 这种方法有效地平衡了准确性和数据效率,这对于临床应用至关重要.
  • RIIR代表了医学图像分析和人工智能驱动的诊断技术的重大进步.