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

Ground-truth-free deep learning for artefacts reduction in 2D radial cardiac cine MRI using a synthetically generated dataset.

Physics in medicine and biology·2021
Same author

Neural networks-based regularization for large-scale medical image reconstruction.

Physics in medicine and biology·2020
Same author

Evaluation of aortic cannula jet lesions in a porcine cardiopulmonary bypass (CPB) model.

The Journal of cardiovascular surgery·2011
Same author

About the polymorphism of the veronal.

Mikrochemie·2010
Same author

Correlation between urodynamic function and 3D cat scan anatomy in neobladders: does it exist?

Neurourology and urodynamics·2009
Same author

Lornoxicam characteristically modulates cerebral pain-processing in human volunteers: a functional magnetic resonance imaging study.

British journal of anaesthesia·2008

相关实验视频

Updated: Jun 29, 2025

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.1K

在低样本的3D膝盖MRI中进行关节重建和细分,结合形状知识和深度学习.

A Kofler1, C Wald2, C Kolbitsch1

  • 1Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany.

Physics in medicine and biology
|March 25, 2024
PubMed
概括

这项研究将统计形状模型 (SSM) 集成到深度学习中,用于3D膝盖MRI重建和细分,以显著降低计算成本实现高精度.

关键词:
深度学习是一种深度学习.重建的重建的重建.细分化 细分化的细分化统计形状模型是一个统计形状模型.

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

2.7K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K

相关实验视频

Last Updated: Jun 29, 2025

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.1K
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
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 适应任务的神经网络 (NN) 优化图像重建的任务,如细分,但需要大量的硬件.
  • 目前的方法通常使用简单的NN构建块,缺乏整合模型特定知识.
  • 端到端可训练的方法提供了潜力,但面临着计算挑战.

研究的目的:

  • 通过结合统计形状模型 (SSM) 来增强端到端可训练的适应任务的图像重建.
  • 将这一点应用于3D膝盖MRI中骨和软骨细分的临床相关问题.
  • 将拟议的方法与同时多任务学习 (MTL) 和复杂的SSMs信息分段管道 (SIS) 进行比较.

主要方法:

  • 扩展了一个端到端可训练的方法与SSMs进行预先信息和规范化.
  • 利用SSM来规范细分图作为后处理步骤.
  • 对重建和细分的MTL和SIS方法进行性能比较.

主要成果:

  • 联合端到端培训和SSM规范化的结合方法显著提高了细分精度,减少了平均和最大表面误差.
  • 实现了与复杂的SIS管道相美的细分质量.
  • 证明模型参数减少了五倍,计算速度提升了一个数量级.

结论:

  • 将SSM集成到MTL中,用于3D膝盖MRI重建和细分,提供了一个计算效率高但高度准确的解决方案.
  • 该方法实现了高质量的细分,即使有显著的低样本 (R=8).
  • 这种方法平衡了深度学习的好处与SSM的先前知识,以改善医疗图像分析.