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

Altered controllability of functional brain networks among electronic cigarettes users with nicotine dependence.

Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco·2026
Same author

Valorization of Sea Buckthorn (<i>Hippophae rhamnocaides</i> L.) Leaves: Polyphenol-Rich Extract Targeting <i>Helicobacter pylori</i> Virulence and Gastric Mucosal Homeostasis.

Journal of agricultural and food chemistry·2026
Same author

Emerging Nanoreactors for Precision Disease Treatment: From Principles to Biomedical Applications.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Exploring the mechanisms of Cangfu Daotan decoction in homotherapy for heteropathy of polycystic ovary syndrome, insulin resistance, infertility, and obesity.

Medicine·2026
Same author

AI-driven digital twins for bone tumors: personalizing immunoradiotherapy and drug-based radiosensitization.

Frontiers in pharmacology·2026
Same author

Integrated in silico design of self-assembled herbal bioactives-polysaccharides nanoformulation for targeted therapy against gastric pathogen Helicobacter pylori.

Carbohydrate polymers·2026

相关实验视频

Updated: Feb 19, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

837

通过经验学驱动的硬度适应性聚焦进行写监督的多器官细分.

Xiaoxiang Han, Yiman Liu, Jiang Shang

    IEEE transactions on medical imaging
    |February 17, 2026
    PubMed
    概括

    这项研究引入了一个以认识论为驱动的框架,以使用有限的草稿注释来改善多器官细分. 它有效地解决了具有挑战性的地区的模型偏差和不确定性,提高了细分精度.

    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:

    • 在多器官细分中,草图监督可以降低注释成本,但却存在稀疏性,导致器官界限等难以理解的领域的特征学习较差.
    • 这种稀疏性导致模型确认偏差和高认识体系不确定性,目前的方法无法充分解决这些问题.

    研究的目的:

    • 提出一种经验驱动的硬度适应性聚焦框架,以克服在多器官细分中涂监督的局限性.
    • 为了减少模型确认偏差和难以分割的地区的认识体系不确定性.

    主要方法:

    • 开发了一种相适应硬度感知损失函数,以量化认识系统的不确定性并生成动态硬度图.
    • 采用分布分歧意识的复制粘贴操作,用于硬样本生成和渐进式学习.
    • 引入特征分布对齐,通过将特定器官的硬区域与全球特征对齐来缓解偏差和不确定性.

    主要成果:

    • 拟议的框架在多器官CT和超声数据集上展示了竞争性性能和有效性.
    • 在跨数据集和受噪声破坏的场景中验证了通用性和稳定性.
    • 该方法为临床应用中高效的注释提供了一个实际的解决方案.

    结论:

    更多相关视频

    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

    3.6K
    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
    04:25

    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

    Published on: December 15, 2023

    3.9K

    相关实验视频

    Last Updated: Feb 19, 2026

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    837
    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

    3.6K
    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
    04:25

    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

    Published on: December 15, 2023

    3.9K
  • 经验驱动的硬度适应性聚焦框架有效地提高了多器官细分的准确性,注释有限.
  • 不确定性量化,硬样本生成和特征对齐的自我改进循环成功地减少了偏见和认识不确定性.
  • 这种方法为优先考虑注释效率的临床环境提供了有价值的工具.