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

Therapeutic Drug Monitoring: Drug Analysis Methods01:26

Therapeutic Drug Monitoring: Drug Analysis Methods

Therapeutic Drug Monitoring (TDM) is a clinical practice that measures specific drug levels in a patient's blood or body tissues to tailor drug therapy effectively. This monitoring is critical for managing drugs with narrow therapeutic indices like digoxin and phenytoin, ensuring they are both safe and effective. For instance, monitoring theophylline levels in asthma patients involves precision and sensitivity to adjust doses according to individual responses to therapy, ensuring efficacy and...

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

Percutaneous endoscopic lumbar discectomy combined with sinuvertebral nerve ablation for lumbar disc herniation with Modic type I endplate changes: a retrospective case-control study.

Asian spine journal·2026
Same author

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026
Same author

MFDSU-Net: a novel semantic-geometric collaborative network for cattle segmentation in complex farm environments.

Frontiers in veterinary science·2026
Same author

Femto- and Attosecond Spectroscopy of Chiral Molecules.

Chimia·2026
Same author

Bioinformatics analysis of pyroptosis-related differentially expressed genes in sepsis and diabetes mellitus.

PloS one·2026
Same author

Catheter-assisted evacuation through limited laminectomy for traumatic long-segment spinal epidural hematoma in ankylosing spondylitis: a technical note and two case reports.

BMC musculoskeletal disorders·2026

相关实验视频

Updated: Jun 19, 2026

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

DMSPS:动态混合软伪标签监督,用于涂监督的医疗图像细分.

Meng Han1, Xiangde Luo2, Xiangjiang Xie1

  • 1School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China.

Medical image analysis
|July 23, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的基于涂的医疗图像细分框架,减少了对广泛的像素级注释的需求. 动态混合软伪标签监督 (DMSPS) 方法显著提高了标签稀疏的细分精度.

关键词:
标注扩展 标注扩展草注释的注释.这是一种软伪标签.不确定性 不确定性软弱监督的学习学习.

更多相关视频

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

384

相关实验视频

Last Updated: Jun 19, 2026

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
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

384

科学领域:

  • 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.
  • 计算机视觉 计算机视觉

背景情况:

  • 准确的医学图像细分需要广泛的像素级注释,这对专家来说是耗时和昂贵的.
  • 使用稀疏标签的弱监督学习提供了一种解决方案,可以减少注释负担,同时保持细分性能.

研究的目的:

  • 为医疗图像细分开发一个高效的基于涂的框架.
  • 为了减少对密集的像素级注释的依赖.
  • 为了提高3D医学成像中的细分精度.

主要方法:

  • 引入了动态混合软伪标签监督 (DMSPS),这是一个基于涂的框架.
  • 使用双分支网络与辅助解码器来增强功能捕获.
  • 利用通过动态混合解码器预测生成的软伪标签进行监督.
  • 实施了一种两阶段的方法来扩大使用低不确定性预测的稀疏涂.

主要成果:

  • 在多个数据集中实现了平均子相似度系数 (DSC) 的显著改善:ACDC (50.46%至89.51%),WORD (75.46%至87.56%) 和BraTS2020 (52.61%至76.53%).
  • 超过了五种最先进的涂监督细分方法.
  • 在不同的细分骨干中证明了可通用性.

结论:

  • DMSPS框架有效地降低了医疗图像细分的注释成本.
  • 拟议的方法在涂监督的医疗图像细分方面实现了最先进的性能.
  • DMSPS是一种强大且可通用的方法,适用于各种医学成像任务.