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

An effective deep learning algorithm for medical image registration.

PLOS digital health·2026
Same author

An iterative-FBP dual-spectral CT reconstruction algorithm based on scatter modeling.

Journal of X-ray science and technology·2025
Same author

Metal artifacts correction based on a physics-informed nonlinear sinogram completion model.

Physics in medicine and biology·2025
Same author

Selecting projection views based on error equidistribution for computed tomography.

Journal of X-ray science and technology·2025
Same author

On a Variational and Convex Model of the Blake-Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images.

Journal of imaging·2021
Same author

Investigating Optimal Time Step Intervals of Imaging for Data Quality through a Novel Fully-Automated Cell Tracking Approach.

Journal of imaging·2021

相关实验视频

Updated: Jul 3, 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

2.8K

自主监督的双域平衡滴块网络用于低剂量CT消噪.

Ran An1,2, Ke Chen3, Hongwei Li1

  • 1School of Mathematical Sciences, Capital Normal University, Beijing, 100048, People's Republic of China.

Physics in medicine and biology
|February 15, 2024
PubMed
概括

本研究介绍了SDBDNet,这是一种新的双域自主监督方法,用于低剂量计算机断层扫描 (LDCT) 测试. 它有效地减少噪音而不会模糊文物,优于现有的方法.

关键词:
双域的排斥是指双域的排斥.低剂量的CT消噪剂自主监督学习学习阴影图解噪音的方法

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

42.6K
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

537

相关实验视频

Last Updated: Jul 3, 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

2.8K
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

42.6K
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

537

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 自主监督学习 (SSL) 对于低剂量计算机断层扫描 (LDCT) 无线化是有效的,但传统方法忽视了sinogram域信息.
  • 现有的双域SSL方法由于LDCT协同图中的噪声不均而与模糊文物作斗争.

研究的目的:

  • 提出SDBDNet,这是一个端到端的双域SSL方法,用于LDCT的拒绝,以减轻模糊的文物.
  • 为了利用sinograms中不均噪声的特性和适度的sinogram-domain denoising来提高图像质量.

主要方法:

  • SDBDNet采用双域方法,在sinogram和图像领域处理数据.
  • 协同图分为子集,以创建具有独立噪声的配对训练数据,然后使用插值和基于学习的校正恢复.
  • 通过Dropblock规范化和denoised和杂的sinograms的加权平均值实现了自适应的sinogram无声化.

主要成果:

  • 在没有引入模糊文物的情况下,SDBDNet在两个领域都表现出有效的无线化.
  • 数字实验证实,SDBDNet的表现优于流行的非学习和现有的自我监督学习方法.

结论:

  • SDBDNet提供了一种新的,高性能的双域SSL解决方案,用于LDCT的拒绝.
  • 该研究强调了合适的sinogram-domain denoising在双域方法中的关键作用,并建议了未来研究的途径.