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

Bound Water as a Reinforcing Element for Ultra-Strong Polyacrylamide.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

CAF-derived PAI-1 serves as an EGFR ligand and fuels KRAS-mutant pancreatic cancer.

Nature communications·2026
Same author

Exploring Dynamic Changes in Empathic Capability Among Postgraduate Nursing Students During Clinical Internships: An Artificial Intelligence-Assisted Qualitative Study With Human-in-the-Loop Validation.

Nurse educator·2026
Same author

Single-cell analysis reveals IL1B<sup>+</sup> macrophages promote lung metastasis in adenoid cystic carcinoma.

Cancer letters·2026
Same author

Disruption of the Circadian Rhythm Induces Acute Pancreatitis via Amino Acid Metabolism-Mediated Macrophage Infiltration.

Cellular and molecular gastroenterology and hepatology·2026
Same author

Integrating network pharmacology, microbiomics, and metabolomics to uncover the therapeutic effect of Liubao tea on osteoarthritis.

Frontiers in immunology·2026

相关实验视频

Updated: Jul 7, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405

CGMA-Net:多层次指导和多尺度聚合网络,用于片细分.

Jianwei Zheng, Yidong Yan, Liang Zhao

    IEEE journal of biomedical and health informatics
    |December 21, 2023
    PubMed
    概括

    本研究介绍了CGMA-Net,这是一个先进的深度学习模型,用于在结肠镜图像中自动化聚细分. CGMA-Net 提高了检测结直肠癌聚体的准确性,有助于早期诊断和患者的治疗结果.

    科学领域:

    • 医疗成像医学成像
    • 人工智能的人工智能
    • 胃肠病学 胃肠病学

    背景情况:

    • 大肠直肠癌 (CRC) 带来了显著的死亡和发病风险.
    • 结肠镜对于预防和控制CRC至关重要.
    • 手动的多胞体细分是耗时的,需要专家的意见.

    研究的目的:

    • 开发用于结肠镜图像的自动化多片细分方法.
    • 解决现有方法的局限性,例如聚和粘膜之间的高度相似性.
    • 为了提高在结肠镜检测中发现多的准确性和效率.

    主要方法:

    • 拟议的跨层面指导和多尺度聚合网络 (CGMA-Net).
    • 集成的跨层次特征指导 (CFG) 区域突出显示.
    • 使用多尺度聚合解码器 (MAD) 来捕获特征依赖.
    • 使用的细节精细化 (DR) 具有异步卷积和对增强细节和整体信息的关注.

    主要成果:

    • 在基准数据集 (Kvasir-SEG和CVC-ClinicDB) 上,CGMA-Net实现了最先进的性能.
    • 在Kvasir-SEG上实现了91.85%的子相似系数 (DSC),在CVC-ClinicDB上达到95.73%.

    更多相关视频

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    8.9K
    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    577

    相关实验视频

    Last Updated: Jul 7, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    405
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    8.9K
    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    577
  • 在各自的数据集上展示了强大的概括能力,DSC得分为86.25%和86.97%.
  • CGMA-Net使用相对较少的参数实现了这些结果.

    • 结论:

    • CGMA-Net 在结肠镜检查中显著推进了自动化多片细分.
    • 拟议的方法为手动细分提供了更有效,更准确的替代方案.
    • 这项技术有可能改善结直肠癌的早期检测和管理.