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

Overview of Microscopy Techniques01:22

Overview of Microscopy Techniques

9.5K
The early pioneers of microscopy opened a window into the invisible world of microorganisms. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes that leveraged nonvisible light, such as fluorescence microscopy that uses an ultraviolet light source and electron microscopy that uses short-wavelength electron beams. These advances significantly improved magnification, image resolution, and contrast. By comparison, the...
9.5K

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

Advances in fully integrated wearable near-infrared spectroscopy: hardware innovations and biomedical applications.

JPhys photonics·2026
Same author

Spatially-resolved optical monitoring of bioreactor cell growth.

Biomedical optics express·2026
Same author

Wearable frequency-domain near-infrared spectroscopy (FD-NIRS) system.

Biomedical optics express·2026
Same author

Feasibility of diffuse Raman spectroscopy to detect in-vivo molecular changes in the tissue induced by subcutaneous implants.

Biomedical optics express·2025
Same author

Elevated glioma-related cortical glutamate <i>in vivo</i> is associated with <i>ex vivo</i> interictal discharges in human brain slices.

Brain communications·2025
Same author

A compact time-domain diffuse optical tomography system for cortical neuroimaging.

Imaging neuroscience (Cambridge, Mass.)·2025

相关实验视频

Updated: May 9, 2025

Universal Hand-held Three-dimensional Optoacoustic Imaging Probe for Deep Tissue Human Angiography and Functional Preclinical Studies in Real Time
09:56

Universal Hand-held Three-dimensional Optoacoustic Imaging Probe for Deep Tissue Human Angiography and Functional Preclinical Studies in Real Time

Published on: November 4, 2014

10.7K

面向实时扩散光学断层扫描,使用手持式扫描探头.

Robin Dale1, Nicholas Ross2, Scott Howard2

  • 1University of Birmingham, Medical Imaging Lab, School of Computer Science, University Rd W, Birmingham, B15 2TT, UK.

Biomedical optics express
|May 5, 2025
PubMed
概括

一个新的深度学习模型使用变压器架构来快速扩散光学断层扫描 (DOT) 成像. 这种方法允许单个模型从各种扫描途径中重建光学特性,提高乳房成像潜力.

更多相关视频

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
00:09

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

6.8K
Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo
12:54

Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo

Published on: October 2, 2021

3.2K

相关实验视频

Last Updated: May 9, 2025

Universal Hand-held Three-dimensional Optoacoustic Imaging Probe for Deep Tissue Human Angiography and Functional Preclinical Studies in Real Time
09:56

Universal Hand-held Three-dimensional Optoacoustic Imaging Probe for Deep Tissue Human Angiography and Functional Preclinical Studies in Real Time

Published on: November 4, 2014

10.7K
Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
00:09

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

6.8K
Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo
12:54

Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo

Published on: October 2, 2021

3.2K

科学领域:

  • 生物医学光学 生物医学光学
  • 医疗成像医学成像
  • 机器学习 机器学习

背景情况:

  • 扩散光学断层扫描 (DOT) 能够高速重建组织光学特性,用于像图像导向乳房成像等应用.
  • 现有的DOT模型是特定于几何的,需要为每一个新的用例进行广泛的数据生成和培训.
  • 这种限制限制了扫描协议和临床环境中的适应性.

研究的目的:

  • 为扩散光学断层扫描 (DOT) 开发一个多功能深度学习模型,克服几何特异性的限制.
  • 为了使一个训练有素的模型能够处理任意的扫描路径和测量密度,用于DOT重建.
  • 提高DOT在临床应用中的速度和适用性,特别是乳腺成像.

主要方法:

  • 提出了一个基于变压器的深度学习架构来编码空间非结构化的DOT测量.
  • 该模型使用模拟数据和模拟乳腺组织的幻影数据进行了训练和验证.
  • 性能是基于根平均平方误差 (RMSE),索伦森-戴斯系数和异常对比度来评估的.

主要成果:

  • 该模型实现了吸收 (μa) 的平均RMSE为0.0095±0.0023cm-1和减少散射 (μs') 的1.95±0.78cm-1.
  • 索伦森-戴斯系数为μa的0.55±0.12和μs的0.67±0.1,异常对比率分别为79±10%和93.3±4.6%.
  • 实现了14 Hz的有效成像速度,平均绝对μa和μs的值在同质实例的地面真相10%以内.

结论:

  • 拟议的基于变压器的DOT模型展示了可适应各种扫描配置的高速重建能力.
  • 这种方法克服了特定几何模型的局限性,为DOT成像提供了更灵活的解决方案.
  • 这些发现支持这种深度学习模型的潜力,用于增强临床乳腺成像和其他DOT应用.