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

Biomarker-guided immunomodulation in septic shock: navigating controversies and therapeutic implications for Critical Care.

Critical care (London, England)·2026
Same author

Engineering Bone-Targeted LNP Delivery of Anti-Sclerostin Antibody mRNA for the Treatment of Osteoporosis.

Journal of biomedical materials research. Part A·2026
Same author

Research progress of artificial intelligence in high-throughput drug screening.

Frontiers in pharmacology·2026
Same author

Engineering of a LysG-derived arginine-specific biosensor for high-throughput screening of arginine overproducers in Corynebacterium glutamicum.

Biotechnology for biofuels and bioproducts·2026
Same author

Structural Evolution and 5f Orbitals Participation in Inverse Sandwich Actinide Boride Clusters: A Theoretical Study of An<sub>2</sub>B<sub>9</sub><sup>-</sup> and An<sub>2</sub>B<sub>10</sub> (An = Th, Pa, U).

Inorganic chemistry·2026
Same author

Studies of chitosan-Prussian blue nanozyme in auditory protection: from cellular mechanisms to <i>in vivo</i> validation.

Frontiers in immunology·2026

相关实验视频

Updated: Jun 8, 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

不确定性 半监督医疗图像细分的全球对比学习框架

Hengyang Liu, Pengcheng Ren, Yang Yuan

    IEEE journal of biomedical and health informatics
    |November 6, 2024
    PubMed
    概括

    本研究引入了一个不确定性全球对比学习 (UGCL) 框架,通过有效处理模糊的边界和不可靠的数据点来提高准确性,以改善半监督的医疗图像细分.

    科学领域:

    • 医疗成像医学成像
    • 计算机视觉 计算机视觉
    • 机器学习 机器学习

    背景情况:

    • 半监督的医疗图像细分面临着模糊的对象界限和有限的标记数据的挑战.
    • 由于数据稀缺和重叠的对象边界,难以准确地对细分边界进行分类.

    研究的目的:

    • 提出一个不确定性全球对比学习 (UGCL) 框架,以解决半监督医疗图像细分中的模糊边界.
    • 通过有效利用不可靠的数据区域来提高细分精度.

    主要方法:

    • 开发了补丁过和分类透过方法,以可靠地生成伪标签.
    • 引入了一个不确定性全球对比学习方法,以利用来自不可靠地区的补充信息.
    • 综合一致性规范化,专注于不可靠的点,以改善细分.

    主要成果:

    • 该UGCL框架成功地区分了模糊的边界和高像素作为不可靠的.
    • 在不确定的点上进行对比学习和一致性规范化显著提高了细分精度.
    • 在两个公共数据集上进行评估,该方法在最先进的技术上显示出了显著的改进.

    结论:

    • 拟议的UGCL框架有效地处理在半监督医疗图像细分中的不可靠数据.

    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

    2.4K
    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

    42.5K

    相关实验视频

    Last Updated: Jun 8, 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

    2.4K
    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

    42.5K
  • 通过对比学习和一致性规范化利用不确定性可以提高细分性能.
  • 该方法提供了一种有前途的方法,以有限的标记数据改进医疗图像分析.