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

相关实验视频

Updated: Jan 16, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

低计数PET图像重建与通用化的稀缺性偏好通过未卷深度网络.

Minghan Fu, Ming Fang, Bo Liao

    IEEE journal of biomedical and health informatics
    |September 29, 2025
    PubMed
    概括

    本研究介绍了GS-Net,这是一种用于 pozitron发射断层扫描 (PET) 图像重建的深度学习模型. 通过结合PET物理,GS-Net提高了图像质量,在临床试验中优于现有方法.

    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

    HMGCR-Driven Cholesterol Metabolism Promotes Osteoarthritis Progression by Accelerating Synovial Fibroblast Senescence.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
    Same author

    Cascade Nanozyme-Catalyzed Tophi Dissolution and ROS Scavenging for Anti-Inflammatory Therapy in Gouty Arthritis.

    Small (Weinheim an der Bergstrasse, Germany)·2026
    Same author

    Influence of ZnO-Decorated Multi-Walled Carbon Nanotubes and Pure-Bore Biopolymers on Shale Chemical Stability and Fluid Loss Control.

    ACS omega·2026
    Same author

    Erratum to: Distinct immune escape and microenvironment between RG-like and pri-OPC-like glioma revealed by single-cell RNA-seq analysis.

    MedScience·2026
    Same author

    [Retracted] BAMBI inhibits inflammation through the activation of autophagy in experimental spinal cord injury.

    International journal of molecular medicine·2026
    Same author

    S-palmitoylation regulates the function of the mitochondria-associated endoplasmic reticulum membrane to alleviate the senescence of nucleus pulposus cells.

    PloS one·2026

    科学领域:

    • 医疗成像医学成像
    • 深度学习 (Deep Learning) 是一种深度学习.
    • 图像重建 图像的重建

    背景情况:

    • 深度学习显示出对低计数正子发射断层扫描 (PET) 图像重建的承诺.
    • 现有的方法往往忽视PET的物理特性,限制了性能和可解释性.

    研究的目的:

    • 介绍GS-Net,一个用于增强PET图像重建的未滚动深度网络.
    • 通过利用PET物理来提高保真度和事先规范化.

    主要方法:

    • 使用Poisson分布和Sparsity学习 (GS-Net) 的通用域转换的最大概率估计.
    • 采用乘数的交替方向方法 (ADMM) 与预期最大化 (EM) 和L1规范优化.
    • 实现端到端的自适应式超参数学习.

    主要成果:

    • 在传统和现有的深度学习方法中,GS-Net表现出优越的性能.
    • 对模拟和真实临床PET数据集的评估显示了显著的改善.
    • 定性和定量分析证实了先进的重建能力.

    结论:

    • 通过整合物理特征,GS-Net为PET图像重建提供了一种新的方法.
    • 该方法实现了最先进的结果,在低计数场景中提高了诊断准确度.
    • 适应式超参数调整简化了这个过程,并提高了概括性.

    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

    1.0K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    735

    相关实验视频

    Last Updated: Jan 16, 2026

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.9K
    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

    1.0K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    735