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

Efficient and Selective Removal of Palladium from Simulated High-Level Liquid Waste Using a Silica-Based Adsorbent NTAamide(C8)/SiO<sub>2</sub>-P.

Nanomaterials (Basel, Switzerland)·2024
Same author

An improved laparoscopic choledochojejunostomy technique (with video).

Asian journal of surgery·2024
Same author

Rational Design of an In-Situ Polymer-Inorganic Hybrid Solid Electrolyte Interphase for Realising Stable Zn Metal Anode under Harsh Conditions.

Angewandte Chemie (International ed. in English)·2024
Same author

Advanced nitrogen and phosphorus removal in pilot-scale anaerobic/aerobic/anoxic system for municipal wastewater in Northern China.

Bioresource technology·2024
Same author

Carbon Nanofibrous Aerogels Derived from Electrospun Polyimide for Multifunctional Piezoresistive Sensors.

ACS applied materials & interfaces·2024
Same author

Laparoscopic Tracer Technique for Liver Lymphatic Drainage by Injecting Indocyanine Green into the Glisson Pedicle.

Annals of surgical oncology·2024

相关实验视频

Updated: Sep 19, 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

3.0K

背景问题:半监督医疗图像分割的交叉视图双向建模框架.

Luyang Cao, Jianwei Li, Yinghuan Shi

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |June 4, 2025
    PubMed
    概括

    本研究介绍了半监督医疗图像细分的交叉视图双向建模 (CVBM). 通过结合背景建模,CVBM提高了前景细分的准确性,甚至超过了完全监督的方法与有限的标记数据.

    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
    • 机器学习 机器学习

    背景情况:

    • 半监督医疗图像细分 (SSMIS) 通过使用未标记的数据,减少了手动注释的需要.
    • 目前的SSMIS方法主要侧重于前景细分,忽视了显式背景建模的潜在好处.

    研究的目的:

    • 为了证明背景建模在提高前景细分信心方面的好处.
    • 为改进SSMIS提出和验证交叉视图双向建模 (CVBM) 框架.

    主要方法:

    • 开发了交叉视图双向建模 (CVBM) 框架,将背景建模作为辅助任务.
    • 实施了双向一致性机制,使前景和背景导向预测一致.
    • 评估了LA,胰腺,ACDC和HRF数据集的框架.

    主要成果:

    • 在多个医疗图像细分数据集中,CVBM实现了最先进的性能.
    • 在胰腺数据集中,CVBM仅使用20%的标记数据超越了完全监督的方法 (DSC:84.57%与83.89%).

    结论:

    • 显式建模背景区域显著增强了SSMIS中的前景细分.
    • CVBM为半监督医疗图像细分提供了一种新且有效的方法,减少了数据注释要求.

    更多相关视频

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    530
    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
    07:13

    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

    Published on: October 27, 2023

    1.4K

    相关实验视频

    Last Updated: Sep 19, 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

    3.0K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    530
    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
    07:13

    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

    Published on: October 27, 2023

    1.4K