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

Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

WeakMitoSAM: competitive prompt aggregation for point-supervised mitochondria segmentation in electron microscopy images.

Biomedical optics express·2026
Same author

SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-Training.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Points-Supervised Fundus Vessel Segmentation via Shape Priors and Contrastive Learning.

IEEE transactions on medical imaging·2025
Same author

Assessing response in endoscopy images of esophageal cancer treated with total neoadjuvant therapy via hybrid-architecture ensemble deep learning.

Frontiers in oncology·2025
Same author

Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation.

IEEE transactions on neural networks and learning systems·2024

相关实验视频

Updated: May 5, 2026

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

43.7K

医疗图像分割多层次非对称对比学习预培训

Shuang Zeng, Lei Zhu, Xinliang Zhang

    IEEE journal of biomedical and health informatics
    |March 3, 2026
    PubMed
    概括
    此摘要是机器生成的。

    本研究介绍了MACL,这是一种用于医疗图像细分的新框架,通过使用多层次表示和同时编码-解码器预训练来增强学习. MACL显著提高了细分的准确性,特别是在有限的标记数据.

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    999

    相关实验视频

    Last Updated: May 5, 2026

    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

    43.7K
    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
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    999

    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:

    • 医疗图像细分至关重要,但由于难以获得专家标记的数据而受到阻碍.
    • 医疗图像的现有对比学习方法往往忽略了多层次表示,并没有充分利用解码器.

    研究的目的:

    • 提出一个新的多层次不对称的对比学习框架 (MACL),以增强医疗图像细分.
    • 通过实现同时进行编码器-解码器预训练和整合多层次表示来解决当前对比学习的局限性.

    主要方法:

    • 开发了一个不对称的对比学习结构,用于同时进行编码器和解码器预训练.
    • 实施了多层次的对比策略,整合了功能级,图像级和像素级的对应.
    • 对8个医学图像数据集的框架进行了评估,与现有的11个对比学习策略进行了对比.

    主要成果:

    • 与其他11种对比学习策略相比,MACL表现优越.
    • 在 ACDC,MMWHS,HVSMR 和 CHAOS 等数据集上实现了显著的子得分改善 (1.72%至7.87%),仅有10%的标记数据.
    • 在5个不同的U-Net骨干中展示了强大的泛化能力.

    结论:

    • 拟议的MACL框架通过利用多层次表示和同时进行编码器-解码器预训练,有效地增强了医疗图像细分.
    • 马克提供了一个有前途的解决方案,以提高细分精度,特别是在低数据的制度,并展现出强大的概括.