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

Neurotransmitter-Informed Connectome Approach to Language Impairment After Stroke.

Stroke·2026
Same author

Prevention in stroke - Current state, present gaps and probable next steps.

Neurological research and practice·2026
Same author

LAMDA: Aiding Visual Exploration of Atomic Displacements in Molecular Dynamics Simulations.

IEEE transactions on visualization and computer graphics·2026
Same author

Deep Learning-Based Quality Control Using Subcellular RNA Spatial Distribution Patterns for Cell Segmentation in Spatial Transcriptomics Data.

Small methods·2025
Same author

Super-Resolution Compatible DNA Labeling Technique Reveals Chromatin Mobility and Organization Changes During Differentiation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Connectivity as a universal predictor of tau progression in atypical Alzheimer's disease.

Brain : a journal of neurology·2025

相关实验视频

Updated: Jul 23, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K

脑卒中-GFCN:使用完全卷积图网络预测缺血性脑卒中病变.

Ariel Iporre-Rivas1,2,3, Dorothee Saur4, Karl Rohr5

  • 1Leipzig University, Institute for Computer Science, Faculty of Mathematics and Computer Science, Signal and Image Processing Group, Leipzig, Germany.

Journal of medical imaging (Bellingham, Wash.)
|July 19, 2023
PubMed
概括

这项研究引入了一个几何深度学习模型,用于从CT输液数据中对脑中风病变进行细分. 这种新的方法证明了改进的精度和适应性损伤边界,超越现有方法.

关键词:
图形神经网络的神经网络机器学习是机器学习.医学成像医学成像多模式成像技术多模式成像技术预测中风 预测中风

更多相关视频

Photothrombotic Ischemia: A Minimally Invasive and Reproducible Photochemical Cortical Lesion Model for Mouse Stroke Studies
08:40

Photothrombotic Ischemia: A Minimally Invasive and Reproducible Photochemical Cortical Lesion Model for Mouse Stroke Studies

Published on: June 9, 2013

35.2K
Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model
05:32

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

2.0K

相关实验视频

Last Updated: Jul 23, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K
Photothrombotic Ischemia: A Minimally Invasive and Reproducible Photochemical Cortical Lesion Model for Mouse Stroke Studies
08:40

Photothrombotic Ischemia: A Minimally Invasive and Reproducible Photochemical Cortical Lesion Model for Mouse Stroke Studies

Published on: June 9, 2013

35.2K
Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model
05:32

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

2.0K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经科学是一个神经科学.

背景情况:

  • 准确的医学图像解释对于急性脑中风诊断和及时的手术干预至关重要.
  • 目前用于脑中风病变的自动细分方法往往缺乏临床可靠性.
  • 计算机断层扫描 (CT) perfusion 参数为中风病变分析提供了丰富的数据.

研究的目的:

  • 用一个新的几何深度学习模型来研究脑中风病变的细分.
  • 为了利用多模 CT perfusion 参数来改善病变检测.
  • 用最先进的方法来评估模型的性能.

主要方法:

  • 提出了一个使用spline卷积和基于图的运算的几何深度学习模型.
  • 在完全卷积式网络架构中的图表上使用的分pooling/pooling运营商.
  • 进行了评估架构超参数的实验,并与现有的细分技术进行比较.

主要成果:

  • 更深层的网络层实现了更高的子系数得分 (DCS),达到0.3654.4.
  • 比例分组方法更好地适应了病变边界,减少了豪斯多夫距离.
  • 该模型的性能与最先进的方法相比,没有高级培训优化.

结论:

  • 拟议的端到端可训练的全卷积图网络有效地从CT输液数据中预测缺血性中风脑病变.
  • 几何深度学习对于复杂的细分任务是可行的,建议的模型表现优于其他模型.
  • 该模型展示了适应不规则的损伤边界的适应性,显示了临床应用的希望.