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

Four-dimensional on-beam computed tomography reconstruction using projection-difference images.

Physics in medicine and biology·2026
Same author

First report of novel single-nucleotide polymorphisms and genetic characteristics in the open reading frame of the prion protein gene (<i>PRNP</i>) in bats.

Frontiers in veterinary science·2026
Same author

Controlled Growth of Au Nanoislands via Repetitive Sputtering and Rapid Thermal Annealing for Nanogap-Rich SERS Substrates.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Source-free domain adaptation for multi-institutional chest X-ray images.

Journal of applied clinical medical physics·2026
Same author

Diffusion prior-guided implicit neural representation for metal artifact reduction in sparse-view CT reconstruction.

Physics in medicine and biology·2026
Same author

X-ray Source Motion Deblurring Framework for Fast Scan in Digital Breast Tomosynthesis.

IEEE transactions on bio-medical engineering·2026

相关实验视频

Updated: Feb 18, 2026

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences
08:19

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences

Published on: May 17, 2018

10.4K

一种基于模拟的CT金属工件减少策略,旨在提高网络通用性.

Sungho Yun1, Subong Hyun1, Da-In Choi1

  • 1Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.

Medical physics
|February 17, 2026
PubMed
概括

这项研究引入了一种新的自主监督深度学习框架,用于计算机断层扫描 (CT) 和金属工件减少 (MAR). 该方法通过整合基于物理的校正和扩散模型来提高图像质量,提高可扩展性和减少没有配对数据的工件.

关键词:
艺术品仿真模拟器件梁硬化校正 梁硬化校正计算机断层扫描 (CT) 是一种计算机断层扫描.潜在的扩散模型.金属工艺品的减少减少多层的感知电子.

更多相关视频

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
06:53

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

6.2K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

743

相关实验视频

Last Updated: Feb 18, 2026

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences
08:19

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences

Published on: May 17, 2018

10.4K
Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
06:53

Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm

Published on: July 23, 2020

6.2K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

743

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算物理 计算物理

背景情况:

  • 现有的计算机断层扫描 (CT) 金属工件减少 (MAR) 深度学习方法往往缺乏明确的物理建模,导致诸如幻觉和解剖扭曲等问题.
  • 这些数据驱动的方法需要广泛的配对数据集,限制它们在不同成像场景中的可扩展性和通用性.

研究的目的:

  • 开发CT MAR的新型自主监督框架,集成基于物理的深度学习,以改善文物减少.
  • 该框架旨在通过将多层感知子 (MLP) 与潜伏扩散模型 (LDM) 结合起来,提高可扩展性,减少幻觉,并保持CT图像的结构忠实性.

主要方法:

  • 一个轻量级的多层感知子 (MLP) 执行物理驱动的多项式对光束硬化进行校正,并结合sinogram一致性进行适应.
  • 该MLP的学习参数模拟来自无文物扫描的文物污染图像,创建伪配对的数据,用于自主监督的条件隐藏扩散模型 (LDM) 训练.

主要成果:

  • 拟议的框架表明,与合成和真实临床数据集上的最先进技术相比,金属工件的减少和结构的保存优越.
  • 在低维隐性空间中运行,隐性扩散模型 (LDM) 显著减少了推断时间,同时保持了高质量的图像重建.

结论:

  • 成功开发了一个自主监督的CT MAR框架,结合了基于MLP的梁硬化校正和有条件的LDM.
  • 该框架允许完全自我监督的培训,没有配对数据,提供强大的文物抑制和结构保存,优于现有方法.