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

Tunable Electrical Transport and Magnetic Anisotropy in Textured SrRuO<sub>3</sub> Films Mediated by Gap Control of Monolayer Ca<sub>2</sub>Nb<sub>3</sub>O<sub>10</sub> Nanosheet Templates.

ACS applied materials & interfaces·2026
Same author

Predicting ICU in-hospital mortality from text-encoded structured EHR data using adaptive transformer layer fusion.

iScience·2026
Same author

Comparative Effects of Different Proteases on the Non-Volatile Taste Compounds and Volatile Flavor Fingerprints of <i>Sarcodon imbricatus</i> Hydrolysates.

Foods (Basel, Switzerland)·2026
Same author

Convergent immune dysregulation in sepsis and colorectal cancer highlights plasma cells and identifies shared candidate genes.

Discover oncology·2026
Same author

Protein <i>S</i>-palmitoylation: Potential strategy for inflammation-related diseases.

Journal of pharmaceutical analysis·2026
Same author

Design and Characterization of a Prototype Pixel Readout Chip for Synchrotron Single Photon-Counting Detectors with 50 µm Pitch and 20 e<sup>-</sup>rms ENC Noise.

Sensors (Basel, Switzerland)·2026

相关实验视频

Updated: Jun 5, 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

基于相互学习的半监督医疗图像细分网络.

Junmei Sun1, Tianyang Wang1, Meixi Wang1

  • 1School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China.

Medical physics
|December 5, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种新的半监督医疗图像细分网络 (MLNet),该网络使用相互学习来防止错误积累. MLNet显著提高了细分精度,在基准数据集上表现优于基线模型.

关键词:
平均教师是指教师.医疗图像细分 医疗图像细分相互学习的相互学习.半监督学习 半监督学习

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

368
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

2.4K

相关实验视频

Last Updated: Jun 5, 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
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

368
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

2.4K

科学领域:

  • 医学图像分析 医学图像分析
  • 机器学习 机器学习
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 半监督学习对于医疗图像细分具有有限的标记数据至关重要.
  • 模型中的过度配置和认知偏差导致错误积累和性能恶化.
  • 现有的方法很难在神经网络训练过程中纠正放大错误.

研究的目的:

  • 开发一种新的学习策略,以提高医疗图像细分的准确性.
  • 为了减轻半监督细分模型中错误知识的持续积累.
  • 提高自动化医疗图像分析的可靠性.

主要方法:

  • 提出了一个名为MLNet的半监督医疗图像细分网络,利用相互学习 (ML) 方法.
  • 采用教师-学生网络架构,模型通过更新参数协作学习.
  • 引入了一个图像部分交换 (IPE) 算法,以最大限度地减少错误的信息,并保持上下文完整性.

主要成果:

  • 在ACDC数据集 (10%标记数据) 上,子系数得到了9.28%的改善,达到89.48%.
  • 在BraTS2019数据集 (10%标记数据) 上表现出强的表现,子系数为84.56%.
  • 在多个指标的准确性和可靠性方面表现优于比较方法.

结论:

  • 拟议的MLNet有效地减轻了半监督医疗图像细分中的错误积累.
  • 与现有方法相比,实验结果证实了该方法的最佳性能和可靠性.
  • 该研究强调了相互学习和有针对性的干扰对强大的医疗图像细分的潜力.