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

Artificial intelligence for detecting acute heart failure on chest CT: prospective clinical proof-of-concept validation.

European radiology experimental·2026
Same author

A fast fully automated approach for evaluating calcified lesions in intravascular ultrasound.

European heart journal. Digital health·2026
Same author

CT-derived density of intracranial arteriosclerosis: a population-based cohort study.

European radiology·2026
Same author

Deep generative models for vessel segmentation in CT angiography of the brain.

Computers in biology and medicine·2026
Same author

Relation between Cerebral Small Vessel Function at 7T MRI and Small Vessel Disease Burden in a General Aging Population.

Cerebrovascular diseases (Basel, Switzerland)·2025
Same author

AI-Based Algorithm to Detect Heart and Lung Disease From Acute Chest Computed Tomography Scans: Protocol for an Algorithm Development and Validation Study.

JMIR research protocols·2025

相关实验视频

Updated: Jun 11, 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

2.7K

标签精细化网络从合成错误增强用于医疗图像细分的标签精细化网络.

Shuai Chen1, Antonio Garcia-Uceda2, Jiahang Su2

  • 1China Electric Power Research Institute Co., Ltd, Beijing, China; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands.

Medical image analysis
|October 5, 2024
PubMed
概括

这项研究引入了一种新的方法来修复医学图像细分中的错误,提高了气道和血管等结构的准确性. 该方法通过从合成生成的错误中学习来提高细分质量.

关键词:
标签的提炼 标签的提炼医学图像 医学图像 医学图像分段化 分段化 分段化 分段化合成错误是一种错误.树木结构形状的形状.

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

376
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

相关实验视频

Last Updated: Jun 11, 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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 用于医学图像分割的深卷积神经网络 (CNN) 通常无法明确学习标签结构.
  • 这可能导致错误的细分,例如树状解剖特征中的断开结构,如气道和血管.

研究的目的:

  • 提出一种新的标签精细化方法,用于纠正初始图像分割中的结构错误.
  • 隐含地将标签结构信息纳入细分精细化过程中.

主要方法:

  • 一种由两个部分组成的新方法: (1) 一个生成合成结构错误的模型和 (2) 一个创建这些合成错误的细分的标签外观模拟网络.
  • 训练一个标签改进网络,使用这些合成错误细分和原始图像来纠正和改进初始细分.

主要成果:

  • 拟议的方法显著优于标准的3D U-Net,之前的四种标签精制方法,以及在气道和脑血管细分任务上的管状结构的专用U-Net.
  • 当使用额外的未标记数据进行培训时,观察到进一步的改善.
  • 一项废除研究证实了拟议方法的各个组件的价值.

结论:

  • 这种新的标签精细化方法有效地纠正了医疗图像细分中的结构错误.
  • 该方法在细分复杂的解剖结构,如气道和血管等方面取得了显著的改进.
  • 该方法为增强基于深度学习的医学图像细分的准确性和可靠性提供了一个有希望的解决方案.