Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Predicting the spread through air spaces in lung adenocarcinoma from preoperative 18 F-FDG PET/CT radiomics.

Nuclear medicine communications·2025

Same author

Assessment of intratumor heterogeneity for preoperatively predicting the invasiveness of pulmonary adenocarcinomas manifesting as pure ground-glass nodules.

Quantitative imaging in medicine and surgery·2025

Same author

Comparative Efficacy of Non-contrast vs. Contrast-enhanced CT Radiomics in Predicting Coronary Artery Plaques Among Patients with Low Agatston Scores.

Academic radiology·2024

Same author

[LSTM-XGBoost Based RR Intervals Time Series Prediction Method in Hypertensive Patients].

Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation·2024

Same author

Iodine concentration, HU accuracy, and metal artifacts evaluation on second-generation dual-layer spectral detector CT images with metal implants: a phantom study.

Acta radiologica (Stockholm, Sweden : 1987)·2024

Same author

Artificial intelligence-based joint attenuation and scatter correction strategies for multi-tracer total-body PET.

EJNMMI physics·2024

Search research articles

相关实验视频

Updated: Jul 24, 2025

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

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

Published on: December 15, 2023

对于PET图像重建的深度通用学习模型.

Qiyang Zhang, Yingying Hu, Yumo Zhao

IEEE transactions on medical imaging

|July 10, 2023

概括

这项研究引入了一种新的深度学习框架,将神经网络与低计数正电子发射断层扫描 (PET) 成像的代优化集成在一起. 该方法提高了图像质量,并恢复了细结构,超过了现有的技术.

更多相关视频

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

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

Published on: November 30, 2022

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

相关实验视频

Last Updated: Jul 24, 2025

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

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

Published on: December 15, 2023

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

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

Published on: November 30, 2022

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
应用数学应用数学应用数学

背景情况:

低计数正子发射断层扫描 (PET) 成像由于其不良的反向问题而带来了重大挑战.
虽然深度学习 (DL) 显示出改善低计数PET图像质量的前景,但现有的DL方法往往会降低精细结构并导致模糊.
将DL与代优化相结合的混合模型可以提高图像质量和结构恢复,但它们的全部潜力仍未得到充分探索.

研究的目的:

提出一种新型的学习框架,将深度学习 (DL) 与基于乘数方法 (ADMM) 的代优化模型的交替方向深度集成为低计数PET成像.
通过创新忠实运算符和在优化框架内将规范化术语泛化来解决现有的DL和混合方法的局限性.
评估拟议的集成DL和ADMM方法与现有技术的性能,使用模拟和真实PET数据.

主要方法:

开发一个深度学习框架,将神经网络与基于ADMM的代优化模型集成在一起.
打破忠诚运营商固有的形式的创新,利用神经网络进行处理.
综合模型中的规范化术语的深度概括.

主要成果:

拟议的综合神经网络方法与基于部分运营商扩展的神经网络方法,标准神经网络拒绝方法和传统代方法相比,表现出更高的性能.
对模拟和真实PET数据的定性和定量评估都证实了拟议方法的有效性.
该方法成功地提高了低数PET图像质量,并恢复了细结构,减轻了常见的降解问题.

结论:

拟议的深度学习框架,将DL与ADMM代优化集成在一起,为低数PET成像提供了显著的进步.
这种新的方法有效地克服了现有方法的局限性,提供了更好的图像质量和更好的细结构恢复.
这些发现表明,通过深度学习和代优化的协同组合,可以开发更强大,更准确的PET成像技术.