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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

14.7K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
14.7K

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

Smiles-based bioactivity prediction through molecular encoder selection and data augmentation.

Journal of cheminformatics·2026
Same author

Token-based fidelity scoring for trustworthy vision transformer interpretations in medical imaging.

International journal of computer assisted radiology and surgery·2026
Same author

Predicting Agitation Stability of Monoclonal Antibodies during Developability Assessment.

Molecular pharmaceutics·2026
Same author

Exact feature collisions in neural networks.

Scientific reports·2026
Same author

A pharmaceutical developability perspective on antibodies with ultra-long CDRs.

Journal of pharmaceutical sciences·2025
Same author

Impact of U2-type introns on splice site prediction in A. thaliana species using deep learning.

BMC bioinformatics·2025

相关实验视频

Updated: Mar 2, 2026

Determining 3D Flow Fields via Multi-camera Light Field Imaging
14:25

Determining 3D Flow Fields via Multi-camera Light Field Imaging

Published on: March 6, 2013

17.2K

在流式成像显微镜中通过基于生成AI的图像合成改进了次可见粒子分类.

Utku Ozbulak1, Michaela Cohrs2, Hristo L Svilenov3

  • 1Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, Republic of Korea; Department of Electronics and Information Systems, Ghent University, Ghent, Belgium; Computational Data Sciences Department, George Mason University Korea, Incheon, Republic of Korea.

Journal of pharmaceutical sciences
|February 28, 2026
PubMed
概括

生成型人工智能扩散模型创建现实的次可见粒子图像,以克服药品分析的深度学习中的数据稀缺和不平衡. 这种方法提高了分类器的性能,用于识别关键颗粒类型,如油和蛋白质聚合物.

关键词:
扩散模型的扩散模型.流成像显微镜的流量成像显微镜.生成性AI是一种人工智能.机器学习 机器学习蛋白质聚合蛋白质的聚合.微观可见粒子 微观可见粒子

更多相关视频

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics
12:26

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Published on: August 27, 2013

18.1K
A Microfluidic Model of Biomimetically Breathing Pulmonary Acinar Airways
09:39

A Microfluidic Model of Biomimetically Breathing Pulmonary Acinar Airways

Published on: May 9, 2016

8.4K

相关实验视频

Last Updated: Mar 2, 2026

Determining 3D Flow Fields via Multi-camera Light Field Imaging
14:25

Determining 3D Flow Fields via Multi-camera Light Field Imaging

Published on: March 6, 2013

17.2K
Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics
12:26

Fabrication, Operation and Flow Visualization in Surface-acoustic-wave-driven Acoustic-counterflow Microfluidics

Published on: August 27, 2013

18.1K
A Microfluidic Model of Biomimetically Breathing Pulmonary Acinar Airways
09:39

A Microfluidic Model of Biomimetically Breathing Pulmonary Acinar Airways

Published on: May 9, 2016

8.4K

科学领域:

  • 制药分析 制药分析
  • 生物技术是生物技术.
  • 人工智能的人工智能

背景情况:

  • 低可见粒子分析对于药物质量控制至关重要,通常使用流成像显微镜和深度学习.
  • 数据稀缺和类不平衡,特别是对于像油和气泡这样的稀有颗粒,阻碍了准确的分类.
  • 现有的方法与不平衡的数据集作斗争,影响识别关键杂质的可靠性.

研究的目的:

  • 开发一种扩散模型,用于生成高准确度的合成粒子图像.
  • 为改善深度学习模型培训,解决次可见粒子数据集中的数据不平衡问题.
  • 提高用于药物颗粒识别的多类分类器的准确性.

主要方法:

  • 开发用于图像生成的最先进的扩散模型.
  • 增强训练数据集的高保真性,合成生成的粒子图像.
  • 使用500,000个蛋白质粒子图像的数据集进行大规模实验验证.

主要成果:

  • 生成的合成粒子图像在视觉质量和结构上与真实图像非常相似.
  • 扩散模型生成的数据有效增强了训练数据集,使强大的多类分类器训练成为可能.
  • 观察到分类性能显著改善,但对准确性没有任何负面影响.

结论:

  • 扩散模型为不平衡粒子分析数据集的数据增强提供了强大的解决方案.
  • 这种生成性AI方法提高了制药质量控制中的深度学习模型的可靠性和准确性.
  • 该研究通过发布扩散模型,训练有素的分类器和集成接口来促进开放式研究.