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

Two poplar cellulose synthase-like D genes, PdCSLD5 and PdCSLD6, are functionally conserved with Arabidopsis CSLD3.

Journal of plant physiology·2013
Same author

Establishment and application of real-time quantitative PCR for diagnosing invasive aspergillosis via the blood in hematological patients: targeting a specific sequence of Aspergillus 28S-ITS2.

BMC infectious diseases·2013
Same author

Comparison of two mathematical prediction models in assessing the toxicity of heavy metal mixtures to the feeding of the nematode Caenorhabditis elegans.

Ecotoxicology and environmental safety·2013
Same author

Trophoblast apoptosis through polarization of macrophages induced by Chinese Toxoplasma gondii isolates with different virulence in pregnant mice.

Parasitology research·2013
Same author

Phase diagram and electronic indication of high-temperature superconductivity at 65 K in single-layer FeSe films.

Nature materials·2013
Same author

[Analyses of clinical features and outcomes of 57 patients with non-gastric MALT lymphoma].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2013

相关实验视频

Updated: Jul 2, 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

2.7K

通过特征分解进行多类医学图像细分的弱监督学习.

Zhuo Kuang1, Zengqiang Yan1, Li Yu1

  • 1School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, China.

Computers in biology and medicine
|February 29, 2024
PubMed
概括
此摘要是机器生成的。

本研究引入了一种新的弱监督学习方法,用于仅使用图像级标签的多类医学图像细分. 该方法有效地处理标签共生和位置相邻性,提高细分精度.

关键词:
医疗图像细分 医疗图像细分多类细分的多类细分.语义上的亲和力 语义上的亲和力软弱的监督 监督的软弱

更多相关视频

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

399

相关实验视频

Last Updated: Jul 2, 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

2.7K
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
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

399

科学领域:

  • 医学图像分析 医学图像分析
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 软弱的监督学习减少了医学图像细分中的深度学习的注释努力.
  • 现有的方法主要集中在单一类细分上,而多类细分未被充分探索.
  • 医疗图像在多类细分中提出了独特的挑战,例如标签共生和位置相邻性.

研究的目的:

  • 开发一种新的弱监督学习方法,用于使用图像级标签进行多类医学图像细分.
  • 为应对医疗图像细分中的标签共生和位置邻近性的挑战.
  • 为了提高自动化医疗图像细分的性能.

主要方法:

  • 一个多级分类网络编码了类特定的二进制预测和类激活地图 (CAM) 的多级特征.
  • 基于语义亲和力的特征分解模块学习类独立和类依赖的特征,以最大限度地提高类间特征距离.
  • 交叉导向损失和相互排斥的损失被用来缓解标签共生和最大限度地减少区域重叠,分别.

主要成果:

  • 拟议的框架在三个数据集的单类和多类医疗图像细分方面都表现出卓越的性能.
  • 该方法有效地解决了标签共生和位置邻近性的挑战.
  • 在弱监督的多类医疗图像细分方面取得了最先进的结果.

结论:

  • 开发的弱监督学习方法为图像级标签的多类医疗图像细分提供了一个有希望的解决方案.
  • 该方法为未来的研究提供了一个基础,以挑战多类细分任务.
  • 这些发现突出了弱监督学习的潜力,以推进医学图像分析.