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

Joint CT reconstruction of anatomy and implants using a mixed prior model.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Investigating 4D respiratory cone-beam CT imaging for thoracic interventions on robotic C-arm systems: a deformable phantom study.

Physical and engineering sciences in medicine·2024
Same author

CT reconstruction using diffusion posterior sampling conditioned on a nonlinear measurement model.

Journal of medical imaging (Bellingham, Wash.)·2024
Same author

Impact of patient habitus and acquisition protocol on iodine quantification in dual-source photon-counting computed tomography.

Journal of medical imaging (Bellingham, Wash.)·2024
Same author

Patient-derived PixelPrint phantoms for evaluating clinical imaging performance of a deep learning CT reconstruction algorithm.

Physics in medicine and biology·2024
Same author

Patient-derived PixelPrint phantoms for evaluating clinical imaging performance of a deep learning CT reconstruction algorithm.

medRxiv : the preprint server for health sciences·2023

相关实验视频

Updated: May 29, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

深度学习CT图像恢复使用系统模糊和噪声模型.

Yijie Yuan1, Grace J Gang1,2, J Webster Stayman1

  • 1Johns Hopkins University, Department of Biomedical Engineering, Baltimore, Maryland, United States.

Journal of medical imaging (Bellingham, Wash.)
|February 5, 2025
PubMed
概括

这项研究引入了一种用于图像修复的新型深度学习方法,该方法使用模糊和噪音信息. 这种方法与仅使用退化图像的模型相比,显著提高了图像质量.

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 图像处理 图像处理

背景情况:

  • 图像恢复对于医学成像等应用至关重要.
  • 当前的深度学习方法经常执行盲目的恢复,缺乏对噪声和模糊特征的了解.
  • 这限制了它们的性能,超出了传统的修复技术.

研究的目的:

  • 开发一种图像恢复方法,将退化的图像输入与系统模糊和噪声特征集成.
  • 将传统的建模方法与深度学习相结合,以实现增强的图像恢复.
  • 为了提高图像质量,如计算机断层扫描.

主要方法:

  • 开发了一种新的深度学习框架,将详细描述模糊和噪声特性的辅助输入纳入其中.
  • 提出了两种集成方法:输入变量和权重变量,允许灵活地纳入卷积神经网络架构.
  • 该模型使用诸如峰值信号噪声比率和结构相似性指数等指标进行评估.

主要成果:

  • 拟议的模型表现出高于没有使用辅助输入的基线模型的性能.
  • 评估证实了基于客观指标的图像恢复质量的改善.
  • 该模型表现出稳健性,即使模糊和噪声参数略有偏离真实值.
关键词:
计算机断层扫描 (CT) 是一种计算机断层扫描.深度学习是一种深度学习.图像恢复恢复 图像恢复

更多相关视频

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

455

相关实验视频

Last Updated: May 29, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

455

结论:

  • 提供对系统模糊和噪声特征的辅助输入的深度学习模型显著提高了图像恢复性能.
  • 这种混合方法为各种应用中图像质量提升提供了更有效的解决方案.
  • 该方法的稳定性表明在现实世界成像场景中具有实际实用性.