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

[Studies on light catalysis oxidation degradation of Malachite Green by Photo-Fenton reagent].

Guang pu xue yu guang pu fen xi = Guang pu·2007
Same author

Alternative conformations of the archaeal Nop56/58-fibrillarin complex imply flexibility in box C/D RNPs.

Journal of molecular biology·2007
Same author

Validation of nonnested and real-time PCR for diagnosis of sheep-associated malignant catarrhal fever in clinical samples.

Journal of veterinary diagnostic investigation : official publication of the American Association of Veterinary Laboratory Diagnosticians, Inc·2007
Same author

Room temperature fabrication of porous ZnO photoelectrodes for flexible dye-sensitized solar cells.

Chemical communications (Cambridge, England)·2007
Same author

Influence of medication choice and comorbid diabetes: the cost of bipolar disorder in a privately insured US population.

Social psychiatry and psychiatric epidemiology·2007
Same author

Mechanistic studies of the long chain acyl-CoA synthetase Faa1p from Saccharomyces cerevisiae.

Biochimica et biophysica acta·2007

相关实验视频

Updated: Jan 10, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

725

PMSFINet:用于医疗图像细分的渐进式多尺度特征交互网络.

Yali Peng, Hong Li, Meiyun Wang

    IEEE journal of biomedical and health informatics
    |November 28, 2025
    PubMed
    概括

    我们介绍了PMSFINet,这是一个用于医疗图像细分的新型网络,可以改善多级特征融合和边界保护. 这提高了医疗成像中复杂结构的细分.

    科学领域:

    • 医学图像分析 医学图像分析
    • 计算机视觉 计算机视觉
    • 深度学习 (Deep Learning) 是一种深度学习.

    背景情况:

    • 斯温变压器通过基于窗口的多头自我注意来减少计算复杂性的密集预测任务.
    • 在Swin Transformer中存在医疗图像分割的局限性,特别是在多尺度特征融合和复杂结构的边界保护方面.

    研究的目的:

    • 提出PMSFINet,一个新的医疗图像细分网络.
    • 通过渐进的多尺度特征交互来增强表示学习,以提高细分精度.

    主要方法:

    • 开发了一个渐进式多尺度特征交互 (PMSFI) 模块,配有双尺度窗口交互注意力 (DSWIA) 块,用于高效的计算和跨尺度信息交换.
    • 集成了具有超分辨率,空间注意力的多尺度超分辨率解码器 (MSRD) 和局部相似感知采样器 (LSAS) 来改进细节和增强边界.
    • 采用交叉注意力融合 (CAF) 模块,以混合注意力为双分支特征的动态融合,改善特征互补性.

    主要成果:

    • 在Synapse上获得了84.94%的子得分,在ACDC上达到92.43%,在ISIC2018数据集上达到90.79%.
    • 在各种医学成像任务中表现出强大的概括性和稳定性.
    • 废弃性研究证实了各个拟议成分的有效性.

    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

    3.3K
    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

    3.7K

    相关实验视频

    Last Updated: Jan 10, 2026

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    725
    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

    3.3K
    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

    3.7K

    结论:

    • PMSFINet有效地解决了医疗图像分割的多尺度特征融合和边界保护的局限性.
    • 拟议的网络显示了提高自动化医疗图像分析的准确性和可靠性的巨大潜力.
    • 在各种医学成像模式下,PMSFINet提供了一个强大的解决方案,用于分割复杂和模两可的结构.