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

Brain Imaging01:14

Brain Imaging

235
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans),  magnetic resonance imaging (MRI),  functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
235

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

Pathogen-Specific Evasion of Innate Immunity by Alphaviruses (CHIKV, VEEV, and SINV).

Reviews in medical virology·2026
Same author

A multi-targeted therapeutic strategy for triple-negative breast cancer: the tumor-targeting peptide p28 enhances chemotherapy, induces apoptosis, crosses the blood-brain barrier, and suppresses metastasis.

Apoptosis : an international journal on programmed cell death·2026
Same author

Felis Catus Optimization (FCO): A novel nature‑inspired metaheuristic algorithm.

PloS one·2026
Same author

A bi-level mobility-aware deep reinforcement learning approach for fault-tolerant task offloading in vehicular edge-cloud computing.

Scientific reports·2026
Same author

Rare Intraoperative Presentation of a Coexistent Uterine Cystic Mass and Bilateral Ovarian Cystic Masses.

Cureus·2026
Same author

An ensemble machine learning classifier for Parkinson's disease diagnosis using optical coherence tomography angiography.

Scientific reports·2026

相关实验视频

Updated: Jul 13, 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

无监督深度学习注册模型用于多模式大脑图像.

Samaneh Abbasi1, Alireza Mehdizadeh2, Hamid Reza Boveiri3

  • 1Department of Medical Physics and Engineering, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.

Journal of applied clinical medical physics
|October 12, 2023
PubMed
概括

这项研究引入了一种新的无监督深度学习模型,用于准确和快速的多式联机大脑图像联合注册. 该方法达到高精度,使其适合临床应用.

关键词:
卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.医疗图像注册 医疗图像注册没有监督的学习学习.

更多相关视频

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

48.1K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K

相关实验视频

Last Updated: Jul 13, 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
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

48.1K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经科学是一个神经科学.

背景情况:

  • 多模式图像注册对于图像导向干预至关重要,但由于复杂的多模式关系而具有挑战性.
  • 目前的监督深度学习方法需要大量的基础真相数据,并且可能偏向注释结构.
  • 无监督学习为克服医疗图像注册监督方法的局限性提供了一个替代方案.

研究的目的:

  • 开发一种基于深度无监督卷积神经网络 (CNN) 的新型模型,用于对脑电脑断层扫描 (CT) 和磁共振 (MR) 图像的同源联合注册.
  • 为了应对与多式联络图像注册监督方法相关的数据要求和潜在偏差的挑战.

主要方法:

  • 一种新的深度无监督CNN模型被设计用于CT/MR脑图像的同源注册.
  • 使用了来自110名神经精神病患者的1100个CT/MR切片对的数据集.
  • 使用12个地标,目标注册错误 (TRE),子相似性,豪斯多夫和贾卡德系数来评估性能.

主要成果:

  • 拟议的无监督模型实现了9.89的TRE,0.79的子相似性,7.15的豪斯多夫距离和0.75的贾卡德系数.
  • 图像记录在有效的203毫秒内完成,证明了临床可行性.
  • 该方法在准确性和计算时间方面,与现有方法相比,显示出具有竞争力的性能.

结论:

  • 开发的无监督深度学习模型为多模式大脑图像注册提供了准确有效的解决方案.
  • 该模型的速度和精度使其非常适合临床图像引导干预.
  • 这种方法为监督方法提供了一个有希望的替代方案,减少了对大量注释数据的依赖.