Jove
Visualize
联系我们

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

Academic burnout and internet gaming disorder in Chinese adolescents: The chain mediating roles of depressive symptoms and negative attentional bias.

Pediatric investigation·2026
Same author

Precise estimation of tissue microstructure with hybrid graph transformer.

Artificial intelligence in medicine·2026
Same author

White spot syndrome virus IE1 protein hijacks the host pentose phosphate pathway to fuel viral replication.

PLoS pathogens·2026
Same author

Association Between Pupil Area and the Efficacy of Peripheral Defocus Spectacle Lenses in Myopia Control.

Translational vision science & technology·2026
Same author

Multimodal Contrastive Prototype Learning for Resilient Brain Tumor Segmentation With Missing Modalities.

IEEE journal of biomedical and health informatics·2025
Same author

Fusing Semantic and Structural Features for Code Error Detection.

Entropy (Basel, Switzerland)·2025
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

相关实验视频

Updated: Jul 19, 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

多任务对比学习用于半监督的医疗图像细分,具有多尺度不确定性估计.

Chengcheng Xing1, Haoji Dong1, Heran Xi2

  • 1School of Computer Science and Technology, Heilongjiang University, Harbin, 150000, People's Republic of China.

Physics in medicine and biology
|August 16, 2023
PubMed
概括
此摘要是机器生成的。

本研究引入了用于医疗图像细分的新半监督学习框架,有效地解决了使用多任务对比学习和多尺度不确定性估计来提高细分精度的类不平衡.

关键词:
相反的学习学习学习.医疗图像细分 医疗图像细分多任务学习是多任务学习.半监督学习 半监督学习不确定性估计估计的不确定性

更多相关视频

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442

相关实验视频

Last Updated: Jul 19, 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
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442

科学领域:

  • 医疗图像分析 医学图像分析
  • 计算机视觉 计算机视觉 计算机视觉
  • 机器学习是机器学习.

背景情况:

  • 自动化医疗图像细分对于疾病诊断和治疗至关重要.
  • 医学数据中的阶级不平衡对准确的细分构成了挑战,特别是对于代表性不足的阶级.
  • 由于数据不平衡,现有的半监督方法与杂的伪标签和不清晰的界限作斗争.

研究的目的:

  • 为半监督医疗图像细分开发一种新的框架,有效地处理阶级不平衡.
  • 为了提高医疗图像中尾部类的细分精度.
  • 提高半监督学习中生成的伪标签的稳定性和质量.

主要方法:

  • 一个采用学生-教师模式的多任务对比学习框架.
  • 在编码器中进行全球图像级对比学习,以减轻类不平衡.
  • 在解码器中进行本地像素级对比学习,用于类内聚合和类间分离.
  • 多尺度不确定性意识一致性损失以减少伪标签噪声.

主要成果:

  • 拟议的方法在ACDC,LA和LiT数据集上显著优于最先进的半监督细分技术.
  • 与现有方法相比,证明了优越的细分性能.
  • 在细分具有挑战性的尾部类中实现了更高的准确性.

结论:

  • 多任务对比式学习有效地解决了阶级不平衡,从而改善了细分结果.
  • 多尺度不确定性估计提高了伪标签的可靠性,提高了整体性能.
  • 该框架为准确的半监督医疗图像细分提供了一个有希望的解决方案.