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

Iron drives protease-independent cleavage of gasdermin D in allergic airway diseases.

Cell·2026
Same author

Leptin-induced autophagy regulates the immunomodulatory potential of adipose-derived mesenchymal stem cells through down regulating the expression of TSG-6.

Scientific reports·2026
Same author

Deep learning analysis of trajectories and spatial variations in HPV vaccine discussions on Chinese Weibo.

Communications medicine·2026
Same author

Protein hydrolysates and xanthine oxidase inhibitory peptides from sunflower capitulum exert antihyperuricemic effects: a comprehensive study based on serum metabolomics and gut microbiota analysis.

Food & function·2026
Same author

Comparative Microbiota and Metabolite Profiles of Undried and Dried Typica Luwak (Civet) Coffee Beans.

Foods (Basel, Switzerland)·2026
Same author

Acute stress alleviates type 2 lung inflammation by restricting ILC2s through corticosterone-glucocorticoid receptor signaling.

Cellular & molecular immunology·2026

相关实验视频

Updated: Jul 23, 2025

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

2.8K

在没有医疗图像细分源数据的情况下,用于多源域调整的双一致的伪标签生成.

Binke Cai1, Liyan Ma1, Yan Sun1

  • 1School of Computer Engineering and Science, Shanghai University, Shanghai, China.

Frontiers in neuroscience
|July 12, 2023
PubMed
概括

这项研究引入了一种新的多源,无源域适应框架,用于医疗图像细分. 该方法在视网膜血管细分方面实现了高灵敏度,解决了隐私问题,而不需要源数据.

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 无监督域调整 (UDA) 允许模型在没有标记目标数据的情况下对新域进行概括.
  • 医疗图像细分面临挑战,因为数据分布多样化和隐私问题限制了数据共享.
  • 现有的UDA方法通常需要访问源数据,这对于敏感的医疗信息来说是不可行的.

研究的目的:

  • 为医疗图像细分提出一个新的多源和无源 (MSSF) 域调整框架.
  • 开发一种方法,只使用源域细分模型来调整模型,而无需访问源数据.
  • 为解决与医疗图像数据共享相关的隐私问题.

主要方法:

  • 引入了双重一致性约束 (域内和域间) 以生成高质量的伪标签.
  • 开发了一种渐进式损失最小化方法,以提高跨域的特性一致性.
  • 实施了一个框架,在没有直接访问医疗图像源的情况下进行培训.

主要成果:

  • 在MSSF条件下实现了视网膜血管细分的最先进性能.
  • 与现有方法相比,以显著的差距显示出最高的灵敏度指标.
  • 验证了拟议的双一致性和最小化技术的有效性.
关键词:
多个来源的多元化.视网膜血管细分器的细分语义细分 语义细分 语义细分 语义细分没有源码的免费源码.无监督的域名适应

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

相关实验视频

Last Updated: Jul 23, 2025

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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

结论:

  • 拟议的MSSF框架对于医学图像细分,特别是视网膜血管细分是有效的.
  • 这种方法成功地克服了医疗AI中数据可访问性和隐私方面的局限性.
  • 未来的工作重点应该是平衡高灵敏度与整体准确度.