Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

VIVIE: Virtually Integrated Ventricular Intervention Environment and its effectiveness as a teaching and learning tool.

International journal of computer assisted radiology and surgery·2026

Same author

Deep learning for synovial volume segmentation of the first carpometacarpal joint in osteoarthritis patients.

Osteoarthritis imaging·2026

Same author

Hippocampal volume for prediction of working memory performance in patients with infantile hydrocephalus.

Journal of neurosurgery. Pediatrics·2026

Same author

Domain-agnostic Unsupervised Domain Adaptation Segmentation from 3D Carotid Artery Ultrasound Image.

IEEE journal of biomedical and health informatics·2026

Same author

Automated extraction of the plane of minimal hiatal dimensions and mid-sagittal plane from 3D transperineal ultrasound.

Medical physics·2026

Same author

Subcortical morphological alterations and volume loss in infantile hydrocephalus: A surface- and volume-based analysis.

Neuroimage. Reports·2026

Search research articles

相关实验视频

Updated: Jun 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

半监督学习框架与形状编码用于新生儿心室细分从3D超声波.

Zachary Szentimrey¹, Abdullah Al-Hayali¹, Sandrine de Ribaupierre²

¹School of Engineering, University of Guelph, Guelph, Ontario, Canada.

Medical physics

|June 10, 2024

概括

这项研究引入了一种新的半监督学习 (SSL) 方法,用于在3D超声图像中对新生儿大脑心室进行细分,显著提高了准确性和效率. 开发的SSL方法有效地利用未标记的数据,在准确性和计算需求方面超过现有方法.

关键词:

3D 超声波 3D 超声波大脑细分的细分大脑细分新生儿大脑的新生儿大脑半监督学习半监督学习

更多相关视频

Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin

Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin

Published on: August 25, 2022

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

相关实验视频

Last Updated: Jun 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin

Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin

Published on: August 25, 2022

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

科学领域:

医学成像医学成像
医学中的人工智能.
新生儿神经成像新生儿神经成像

背景情况:

三维 (3D) 超声波 (美国) 对监测新生儿腹腔内出血有前途.
在3D US中对侧腔室进行准确的细分是具有挑战性的,因为边界差,信号与噪声比低.
完全监督的方法需要大量的医生注释,导致高成本和潜在的过度装配.

研究的目的:

开发一个快速,轻量级,准确的半监督学习 (SSL) 方法用于3D美国图像细分.
利用未标记的数据来提高新生儿大脑侧心室的细分性能.

主要方法:

提出了一个SSL框架,结合了形状编码的自动编码器和3DU-Net细分模型.
使用自动编码器的伪标签来执行形状约束,以及用于数据分布分析的对抗性区分器.
用887张3D美国图像 (87张有标签,800张没有标签) 进行实验,并使用子相似系数 (DSC),平均绝对表面距离 (MAD) 和绝对体积差异 (VD) 进行性能比较.

主要成果:

形状编码SSL方法在不同数据分割中实现了平均DSC改进6.5%,7.7%和4.1%的基线3D U-Net.
该方法证明了计算效率,与基线相比,RAM仅增加1GB,RAM/参数比3D U-Net组合少.
使用威尔科克森签名等级测试与邦费罗尼校正 (p < 0.01) 证实了统计学意义.

结论:

本文介绍了第一个专门用于3D美国器官细分的SSL方法之一,它结合了新生儿大脑侧腔室的未标记数据.
与最先进的SSL和完全监督的方法相比,提出的SSL方法实现了优越的DSC和较低的VD.
这种方法在计算上是高效的,为医疗图像细分挑战提供了实际的解决方案.