相关实验视频

Updated: Jan 18, 2026

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Published on: May 24, 2021

通过连续场和矢量流量模拟缺血性中风病理动力学

Liuxi Chu^1,2, Ying Wang³, Zhijin Li⁴

¹National Key Laboratory of Macromolecular Drugs and Large-scale Preparation, School of Pharmaceutical Sciences, Wenzhou Medical University, Wenzhou, Zhejiang, China. clx0605@wmu.edu.cn.

NPJ digital medicine

|January 16, 2026

概括

StrokeFlow是一种新的深度学习方法,可以准确地将缺血性中风区域绘制为连续场,改善小病变的检测,并提供比传统的二进制面具更详细的信息.

科学领域:

医疗成像医学成像
人工智能的人工智能
神经学神经学

背景情况:

在扩散权重MRI (DWI) 中精确地定位 perfusion 缺陷对于管理急性缺血性中风至关重要.
当前的深度学习模型产生离散的二进制面具,失去关键的损伤内部信息,并且无法代表缺血损伤的连续性.

研究的目的:

引入StrokeFlow,这是一个用于将缺血区域表示为连续场的新框架.
开发一个基于坐标的网络,生成一个平滑的缺血密度场,用于 voxel-level 心脏病发作概率.
结合一个向量流量头,以使用显微扩散系数 (ADC) 地图梯度来建模 perfusion deficit 的方向性.

主要方法:

开发了一个新的基于坐标的深度学习网络 (StrokeFlow).
训练网络以输出连续的缺血密度场.
实现了由ADC地图的负梯度监督的矢量流头.

主要成果:

在ISLES 2022数据集上,StrokeFlow实现了优异的损伤边界精度,在95%的豪斯多夫距离中显著超过了基线.
该模型在检测小型和多焦点缺血病变时表现出更高的灵敏度.
与离散细分相比,连续现场表示提供了更具生物学可信性和可解释性的结果.

结论:

对于缺血性中风的评估,StrokeFlow将范式从离散细分转变为连续的,功能意识的领域.
该框架为评估急性缺血性中风中 perfusion 缺陷提供了一个更加细致和临床价值的工具.
这种方法提高了基于MRI的中风分析的精度和可解释性.

更多相关视频

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Modeling Stroke in Mice - Middle Cerebral Artery Occlusion with the Filament Model

Published on: January 6, 2011

Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis

Modeling Stroke in Mice: Focal Cortical Lesions by Photothrombosis

Published on: May 6, 2021

相关概念视频

Regulation of Stroke Volume

Regulation of Stroke Volume

The regulation of stroke volume, which is the amount of blood the heart pumps out during each heartbeat, is critical for maintaining a healthy circulatory system. Stroke volume is influenced by three main factors: preload, contractility, and afterload.
Preload refers to the degree of stretch on the heart before it contracts. It's analogous to the stretching of a rubber band; the more it's stretched, the more forcefully it snaps back. This concept is encapsulated in the Frank-Starling law of the...