通过机器学习对缺血性中风或短暂缺血性发作进行液体减弱倒置恢复MRI的自动化评分
Eun-Tae Jeon1, Seung Min Kim2, Jin-Man Jung3,4
1Department of Neurology, Korea University Ansan Hospital, University College of Medicine, Ansan, South Korea.
Scientific reports
|September 1, 2025
概括
这项研究开发了一个自动化的深度学习系统,用于对中风患者的白质超强度 (WMH) 进行分级. 人工智能模型准确地对WMH进行细分,并预测Fazekas的分数,为评估中风相关的大脑变化提供了可靠的工具.
科学领域:
- 神经学
- 医学成像
- 人工智能
背景情况:
- 白质超强度 (WMH) 是中风患者的关键成像生物标志物,通常通过主观的Fazekas尺度进行评估.
- 现有的WMH分级深度学习模型在中风患者中应用有限.
研究的目的:
- 开发和验证用于中风患者的WMH细分和Fazekas分级的自动深度学习管道.
- 使用空间概率学方法提高WMH评估的准确性.
主要方法:
- 创建了一个两步深度学习管道,使用基于U-Net的残余神经网络进行WMH细分和3D卷积神经网络进行Fazekas分级.
- 这些模型在471名中风患者的T2加权FLAIR图像上进行了训练和验证.
主要成果:
- WMH细分模型实现了0.81的AUPRC和0.73的Dice系数. WMH体积预测的平均绝对误差为3. 1毫升.
- 在一致性分析中观察到强烈的一致性 (R平方=0. 91,CCC=0. 96内部).
- 深度学习模型在Fazekas得分预测中实现了高二次加权的kappa值 (0. 951- 0. 956),在内部和外部验证中表现出强的表现.
结论:
- 开发的深度学习管道为中风患者提供了准确和高效的自动WMH细分和Fazekas分级.
- 这种自动化方法可以作为评估WMH负担和潜在预测未来血管事件的可靠工具.
更多相关视频
相关概念视频
01:24Magnetic Resonance Imaging
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
01:21Imaging Studies for Cardiovascular System IV: CMRI
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...