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

Application of integrated whole-course clinical learning combined with case-based learning in undergraduate otolaryngology clerkships.

BMC medical education·2026
Same author

Precision prebiotics: Engineering food-derived polysaccharides to target specific SCFA-producing taxa for neuroprotection via the microbiota-gut-brain axis.

Current research in food science·2026
Same author

A Multi-Task Segmentation and Classification Network Based on Ultrasound Images for Predicting the Grading of Ascites in the Abdominal Cavity.

Ultrasonic imaging·2026
Same author

Targeting the Myocardial Microenvironment: Novel Antiviral Strategies and Therapeutic Perspectives for Coxsackievirus B-Induced Myocarditis.

Journal of the American Heart Association·2026
Same author

Developing High Performance N-Oxygenase for Azomycin Synthesis through Ancestral Sequence Reconstruction.

ACS synthetic biology·2026
Same author

Application of single-cell transcriptomic technology in cell fate determination of embryonic liver.

Histology and histopathology·2026

相关实验视频

Updated: May 20, 2025

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population
09:02

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

366

一个多任务的神经网络,用于全波形超声波骨成像.

Peiwen Li1, Tianyu Liu2, Heyu Ma2

  • 1Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200438, China.

Computer methods and programs in biomedicine
|May 1, 2025
PubMed
概括
此摘要是机器生成的。

这项研究介绍了CEDD-Unet,这是一种新的深度学习方法,用于使用超声波进行高分辨率的骨成像. 与现有方法相比,CEDD-Unet显著提高了声速 (SOS) 重建的准确性,并减少了文物.

关键词:
骨成像技术 骨成像技术深度学习是一种深度学习.全波形逆转 (FWI) 是指波形的全逆转.多任务学习多任务学习超声波成像 超声波成像

更多相关视频

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging
12:00

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Published on: March 2, 2015

12.1K
Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments
07:52

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Published on: June 28, 2024

907

相关实验视频

Last Updated: May 20, 2025

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population
09:02

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

366
Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging
12:00

Non-invasive Parenchymal, Vascular and Metabolic High-frequency Ultrasound and Photoacoustic Rat Deep Brain Imaging

Published on: March 2, 2015

12.1K
Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments
07:52

Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments

Published on: June 28, 2024

907

科学领域:

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

背景情况:

  • 由于骨的复杂结构和声学特性,超声波骨成像具有挑战性.
  • 传统的骨图像全波形反转 (FWI) 产生了人工制造物,需要大量的计算资源.

研究的目的:

  • 开发一种基于深度学习的FWI方法,用于高分辨率的超声波骨图像.
  • 克服骨图像中的传统FWI的局限性,例如局部最小陷和计算负担.

主要方法:

  • 提出了一种新的卷积式LSTM (ConvLSTM) 和高效多尺度注意力 (EMA) 增强的双解码器U-Net (CEDD-Unet).
  • CEDD-Unet重建了声速 (SOS) 模型,并确定了骨软组织边界.
  • 利用超声波无线电频率 (RF) 信号进行多尺度特征提取.

主要成果:

  • 在人类和小鼠骨数据集上,CEDD-Unet在精度 (较低的MAE) 和图像质量 (更高的SSIM,PSNR) 方面超过了现有的方法.
  • 实现了更清晰的骨边界,减少了文物,并改善了与基本真相的一致性.
  • 与传统的FWI相比,证明了计算成本的降低,并消除了对初始模型的需求.

结论:

  • CEDD-Unet显示了使用超声波的高分辨率骨成像的重大前景.
  • 该方法可以重建准确的,尖的骨SOS模型.
  • 这种深度学习方法为肌肉骨超声波成像提供了潜在的进步.