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

Study on the characteristics of carotid wall shear stress in type 2 diabetes patients based on ultrasound vector flow imaging.

Frontiers in endocrinology·2024
Same author

Enhanced pediatric thyroid ultrasound image segmentation using DC-Contrast U-Net.

BMC medical imaging·2024
Same author

Contrast U-Net driven by sufficient texture extraction for carotid plaque detection.

Mathematical biosciences and engineering : MBE·2023
Same author

Assessment of left ventricular function in patients with type 2 diabetes mellitus by non-invasive myocardial work.

Frontiers in endocrinology·2023
Same author

Measurement of left ventricular fluid dynamic parameters in healthy Chinese adults based on echocardiographic vector flow mapping.

Chinese medical journal·2023
Same author

G6PD inhibits ferroptosis in hepatocellular carcinoma by targeting cytochrome P450 oxidoreductase.

Cellular signalling·2021

相关实验视频

Updated: Jun 21, 2025

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents
08:02

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

Published on: July 16, 2020

4.8K

在超声波定位显微镜中高效的微气泡轨迹跟踪使用式循环单元式多任务临时神经网络.

Yuting Zhang, Wenjun Zhou, Lijie Huang

    IEEE transactions on ultrasonics, ferroelectrics, and frequency control
    |July 8, 2024
    PubMed
    概括

    这项研究介绍了一种基于单元的多任务时间神经网络 (GRU-MT),用于高效地跟踪超声波局部化显微镜 (ULM) 中的微气泡轨迹. 通过增强非线性运动建模和时间动态,GRU-MT提高了准确性和实时可行性.

    更多相关视频

    Multi-timescale Microscopy Methods for the Characterization of Fluorescently-labeled Microbubbles for Ultrasound-Triggered Drug Release
    06:02

    Multi-timescale Microscopy Methods for the Characterization of Fluorescently-labeled Microbubbles for Ultrasound-Triggered Drug Release

    Published on: June 12, 2021

    3.9K
    Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
    07:33

    Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

    Published on: March 28, 2025

    353

    相关实验视频

    Last Updated: Jun 21, 2025

    A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents
    08:02

    A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

    Published on: July 16, 2020

    4.8K
    Multi-timescale Microscopy Methods for the Characterization of Fluorescently-labeled Microbubbles for Ultrasound-Triggered Drug Release
    06:02

    Multi-timescale Microscopy Methods for the Characterization of Fluorescently-labeled Microbubbles for Ultrasound-Triggered Drug Release

    Published on: June 12, 2021

    3.9K
    Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
    07:33

    Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

    Published on: March 28, 2025

    353

    科学领域:

    • 医疗成像医学成像
    • 生物医学工程 生物医学工程
    • 人工智能的人工智能

    背景情况:

    • 超声波局部化显微镜 (ULM) 提供非侵入性的微血管成像,但在传统的微泡追踪方面面临挑战.
    • 现有的方法很复杂,阻碍了实时应用,深度学习方法经常忽视时间动态.

    研究的目的:

    • 开发一种新的深度学习模型,以在ULM中高效准确地跟踪微泡轨迹.
    • 为了解决微泡的实时处理和时间运动建模的局限性.

    主要方法:

    • 引入了一个基于单元的多任务时间神经网络 (GRU-MT),用于同时进行轨迹跟踪和优化.
    • 改进了非线性运动模型,以更好地捕捉微泡动力学.
    • 评估了各种时间神经网络 (RNN,LSTM,GRU,变压器) 用于微泡追踪.

    主要成果:

    • 在模拟和体内生物数据集中,GRU-MT表现出卓越的非线性建模和稳定性.
    • 拟议的方法实现了轨迹跟踪误差的减少,特别是在更短的时间间隔.
    • GRU-MT显示了有效的实时微气泡轨迹跟踪的潜力.

    结论:

    • GRU-MT为ULM提供了微气泡轨迹跟踪的重大进步.
    • 该模型处理非线性运动和时间动态的能力提高了跟踪精度和效率.
    • 开源代码促进了该技术的进一步研究和应用.