基于深度学习的自动扫描平面定位用于大脑磁共振成像
Gaojie Zhu1,2, Xiongjie Shen2, Zhiguo Sun2
1Center for Biomedical Imaging Research, School of Biomedical Engineering, Tsinghua University, Beijing, China.
Quantitative imaging in medicine and surgery
|June 7, 2024
概括
这项研究引入了一个深度学习框架,用于准确的,自动化的头部MRI扫描定位,克服手动和传统方法的局限性. 人工智能模型在临床环境中实现了高精度和效率.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 在临床MRI中手动扫描计划是不准确的,不一致的,耗时的.
- 现有的自动化方法缺乏实际使用的准确性,稳定性和计算效率.
研究的目的:
- 开发和评估可靠,准确的深度学习框架,用于自动头部MRI扫描平面定位.
- 将先前的物理知识纳入AI模型以提高性能.
主要方法:
- 一个端到端的深度学习框架,使用级联的3D卷积神经网络来检测里程碑.
- 多尺度特征融合和物理上有意义的回归损失 (PRL,DRL).
- 数据增强策略模拟复杂的临床场景.
主要成果:
- 在229个临床头部MRI扫描中实现了高性能.
- 证明了低点对点绝对误差 (0.872毫米) 和相对误差 (0.10%).
- 报告的平均角误差为0.502°,0.381°和0.675°,适用于斜面,横面和冠面平面.
结论:
- 拟议的深度学习方法提供了高效率,准确性和稳定性.
- 对各种临床头部MRI扫描有效,包括定位变化,对比度,噪音和病理.
相关概念视频
Brain Imaging
226
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
226
Magnetic Resonance Imaging
5.1K
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...
5.1K


