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

Interstitial cystitis as the initial presentation of primary Sjogren's syndrome: A case report.

Medicine·2026
Same author

Rhubarb in renal fibrosis: from traditional ethnopharmacology to mechanistic therapeutic development.

Chinese journal of natural medicines·2026
Same author

CEBPD-MMP8 Axis Contributes to Cardiomyocyte Injury in Septic Shock.

Applied biochemistry and biotechnology·2026
Same author

Extremely low-efficiency roll-off and extended lifetime in hybrid WOLEDs based on a TADF forming co-host interlayer.

Optics letters·2026
Same author

Extraction Optimization, Multi-Dimensional Characterization, and Agricultural Application of Humic Acid from <i>Protaetia brevitarsis</i> Frass Derived from Straw Transformation.

Insects·2025
Same author

Hypermethylated USP44 deubiquitinates SENP2: a critical mechanism in esophageal cancer progression and a new target for intervention.

Clinical epigenetics·2025

相关实验视频

Updated: Jul 4, 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

半监督的低剂量SPECT恢复使用sinogram内部结构感知图形神经网络.

Si Li1, Keming Chen1, Xiangyuan Ma2

  • 1School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, People's Republic of China.

Physics in medicine and biology
|February 7, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了用于低剂量SPECT成像的新型半监督框架,通过利用sinogram内部结构和未标记数据来提高图像质量,以减少辐射暴露.

关键词:
图表神经网络的神经网络低剂量的SPECT检测结果半监督学习 半监督学习阴影图的内部结构.修复阴影图的修复

更多相关视频

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

542
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

相关实验视频

Last Updated: Jul 4, 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
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

542
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

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:

  • 低剂量单光子发射计算机断层扫描 (SPECT) 对于降低辐射风险至关重要.
  • 当前的深度学习方法往往忽略了sinogram的内部结构,需要大量的标记数据.
  • 在监督学习中获取正常剂量的SPECT数据具有挑战性.

研究的目的:

  • 开发一个半监督的框架,用于低剂量的SPECT阴影图复原.
  • 利用图形神经网络利用sinograms固有的内部结构.
  • 利用大量未标记的低剂量数据来提高图像质量.

主要方法:

  • 一个基于UNet的框架,结合了基于sinogram结构的非本地邻居图形神经网络 (SSN-GNN) 和基于窗口的K-最近邻居GNN (W-KNN-GNN).
  • 在培训中使用了平均教师半监督学习方法.
  • 雇佣了XCAT人类形态数字幻影用于数据生成.

主要成果:

  • 拟议的框架在定量和定性评估中表现出优于最先进的方法的性能.
  • 废弃性研究证实了每个组件的有效性,强度实验显示了对不同噪声水平的弹性.
  • 半监督方法有效地利用未标记的数据来增强恢复.

结论:

  • 开发的框架通过利用sinogram内部结构和未标记数据,有效地提高低剂量SPECT图像质量.
  • 这种方法为在SPECT成像中减少辐射剂量提供了有价值的工具,而不会影响图像质量.
  • 西诺格拉姆内部结构意识和半监督策略代表了低剂量SPECT重建的重大进步.