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

PhotIQA: A photoacoustic image data set with image quality ratings.

Scientific data·2026
Same author

The confounding effects of skin colour in photoacoustic imaging.

Nature communications·2026
Same author

SPEND-hSRS imaging of fumarate uncovers mitochondrial metabolic heterogeneity.

bioRxiv : the preprint server for biology·2026
Same author

Early Radiation Therapy Response Assessment Using Multi-Scale Photoacoustic Imaging.

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

Optical coherence tomography and elastography for <i>ex vivo</i> visualization of early gastric cancer.

Journal of biomedical optics·2026
Same author

A guide to reactive oxygen species in tumour hypoxia: measurement and therapeutic implications.

Molecular oncology·2025
Same journal

Reassessing the Proposed Creatine-PrP Axis in Endometriosis: Methodological and Mechanistic Considerations.

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

IL-7R-Enriched Extracellular Vesicles From the Thymus Drive Colitis via Promoting Neutrophil Extracellular Trap Formation.

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

Oral Prebiotic Polysaccharide Hydrogels Sustaining Colon Antibody Release Alleviate Inflammatory Bowel Disease.

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

Systematic Phosphorus-Driven Structural and Field Engineering of n-a-Si:H for Flexible n-a-Si:H/Te Near-Infrared Photodetectors.

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

Chemically Gradient Ordered Nanodomains Enable Large Tensile Ductility in Gigapascal Lightweight Refractory High-Entropy Alloys.

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

Single-Molecule Characterization of Bacterial Factor-Dependent Transcription Activation by Rob.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
查看所有相关文章

相关实验视频

Updated: Jun 23, 2025

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

9.9K

使用深度生成学习对3D微血管光声学图像进行无监督细分.

Paul W Sweeney1,2, Lina Hacker1,2, Thierry L Lefebvre1,2

  • 1Cancer Research UK Cambridge Institute, University of Cambridge, Robinson Way, Cambridge, CB2 0RE, UK.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)
|June 26, 2024
PubMed
概括
此摘要是机器生成的。

一个新的深度学习模型,VAN-GAN,从光声成像数据准确地分割3D血管网络. 这种无监督的方法减少了手动标签,改善了研究中的血管分析.

关键词:
血管是血管中的血管.深度学习是一种深度学习.产生性的产生性.摄影声学 摄影声学细分化 细分化的细分化没有监督的无人驾驶.

更多相关视频

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.0K
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

2.7K

相关实验视频

Last Updated: Jun 23, 2025

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

9.9K
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.0K
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

2.7K

科学领域:

  • 生物医学成像技术 生物医学成像技术
  • 医学图像分析 医学图像分析
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 中镜光声学成像 (PAI) 提供高对比度,无标签的血管网络可视化.
  • 从PAI数据中精确细分3D血管网络对于理解组织生理学和病理学至关重要.
  • 当前的细分方法往往耗时,易出错,需要大量的手动注释.

研究的目的:

  • 从PAI数据开发一个无监督的深度学习框架,用于自动化的3D血管网络细分.
  • 为了减少在PAI分析中依赖手动注释的基准真相标签.
  • 通过学习PAI的物理,创建一个能够细分血管系统的模型.

主要方法:

  • 介绍了船舶细分生成对抗网络 (VAN-GAN),这是一个无监督的图像到图像转换模型.
  • 将类似于真实解剖学的合成血管网络集成到训练过程中.
  • 训练VAN-GAN复制PAI系统的基础物理进行细分.

主要成果:

  • VAN-GAN在各种数据集 (in silico,in vitro,in vivo) 中展示了3D血管网络的准确和公正的细分.
  • 该模型已成功应用于患者衍生乳腺癌异种移植模型和3D临床血管图.
  • 与U-Net (F1分数:0.87) 等监督方法相比,实现了竞争性细分性能 (F1分数:0.84).

结论:

  • VAN-GAN提供了一个强大的,无监督的解决方案,用于从PAI数据中对3D血管网络进行细分.
  • 使用合成数据和基于物理的学习降低了高质量的血管细分的障碍.
  • 这种方法有可能显著提高血管结构和功能的临床前和临床研究.