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

Residual metal single-atom catalysis: enhanced photocatalytic hydrogen production <i>via</i> ligand-modulated d-orbital splitting.

Chemical science·2026
Same author

Biodegradation of cyano liquid crystal monomers by an aerobic enrichment culture: Key degraders and interspecies synergistic mechanisms.

Water research·2026
Same author

Development of nontarget method based on GC-QTOF-HRMS for analyzing organic pollutants in human serum.

Journal of environmental sciences (China)·2026
Same author

Exploratory Study on Plasticiser Intake During Intermittent Fasting: Effects on Weight, Glycaemic Control and Vitamin D Levels in Type 2 Diabetes.

Toxics·2026
Same author

Resistance Mechanisms of Alectinib in ALK-Positive Non-Small Cell Lung Cancer and Therapeutic Strategies.

Current cancer drug targets·2026
Same author

Co-exposure profiles of PAHs and their derivatives in coking plant workers' serum and associations with liver function.

Environment international·2026

相关实验视频

Updated: Jul 17, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K

自动转移监督目标方法用于用CT成像对肺病变区域进行细分.

Peng Du1, Xiaofeng Niu2, Xukun Li2

  • 1Hangzhou AiSmartIoT Co., Ltd., Hangzhou, Zhejiang, China.

BMC bioinformatics
|September 4, 2023
PubMed
概括

这项研究引入了一种半监督的深度学习方法,用于在CT扫描中对肺部感染进行细分,通过使用自动生成的精细标签来提高学习效率来提高准确性.

关键词:
具有成本效益的成本效益.双分支模型的模型是双分支的伪标签 伪标签是一个假的标签.肺部疾病 肺部疾病

更多相关视频

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

542

相关实验视频

Last Updated: Jul 17, 2025

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.5K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

542

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机辅助诊断 计算机辅助诊断

背景情况:

  • 在CT图像中精确细分感染的肺部区域对于诊断和治疗至关重要.
  • 传统的方法往往依赖于广泛的手动注释,这是耗时和劳动密集的.
  • 开发自动化或半自动化方法可以显著提高效率和可扩展性.

研究的目的:

  • 提出一种新的半监督双分支框架,用于自主识别和选择最佳目标,以在CT图像中对感染的肺部区域进行细分.
  • 通过利用专家注释和自动生成,粗略注释的数据来提高学习效率.
  • 为了提高医疗图像细分的深度学习模型的准确性.

主要方法:

  • 设计了一个半监督的双分支框架,包含有限的专家注释数据和大量粗略注释数据 (使用Hu值进行细分).
  • 在培训期间,使用Lovasz评分方法在弱势分支中动态切换和选择最佳监督目标.
  • 这种方法使模型能够利用噪音标签进行初始定位,并使用更准确的数据逐步完善目标.

主要成果:

  • 拟议的半监督双分支网络在内部基准上达到83.56±12.10%,在外部基准上达到82.67±8.04%的平均子相似系数 (DSC).
  • 与没有额外样本的U-Net和平均教师算法相比,拟议的方法显示了DSC值的显著改善 (在内部和外部基准上分别高达13.54%和13.37%).
  • 使用具有成本效益的伪标记样品显著提高了模型性能.

结论:

  • 具有成本效益的伪标签样本有效地协助深度学习 (DL) 模型培训,优于仅在手动标签上训练的传统DL模型.
  • 与现有的双分支结构相比,拟议的方法显示出更高的性能.
  • 这种方法为医疗图像细分任务提供了可扩展和高效的解决方案.