使用深度学习网络进行动脉自旋标记MRI的同源图像注册
Zongpai Zhang1, Huiyuan Yang1, Yanchen Guo1
1Department of Computer Science, State University of New York at Binghamton, Binghamton, NY 13902, USA.
NeuroImage
|August 3, 2023
概括
与现有方法相比,一种新的卷积神经网络 (CNN) 方法,即亲缘注册网络 (ARN),显著提高了低信号对噪声比率 (SNR) 动脉旋转标记 (ASL) perfusion 功能MRI (fMRI) 图像的准确性和速度.
科学领域:
- 医疗成像医学成像
- 神经成像是一种神经成像.
- 机器学习 机器学习
背景情况:
- 卷积神经网络 (CNN) 擅长记录高信号噪声比 (SNR) 的结构性MRI.
- 功能性MRI (fMRI) 中的低SNR,例如动脉旋转标记 (ASL) perfusion fMRI,对准确的图像记录提出了挑战.
- 对于低SNRASLfMRI注册的CNN的有效性仍然不清楚.
研究的目的:
- 调查基于CNN的亲属注册网络 (ARN) 的可行性,以注册低SNR的3D ASL perfusion fMRI时间序列.
- 将RNA的性能与最先进的统计参数映射 (SPM) 算法进行比较.
- 评估RNA的准确性,速度和泛化能力.
主要方法:
- 开发了一种RNA来学习ASL fMRI数据的六个相关参数.
- 使用模拟运动和真实ASL fMRI采集训练了RNA.
- 应用来自RNA的转换来生成注册图像.
- 在模拟和真实ASLfMRI数据集上比较RNA与SPM,包括对冥想,双相情感障碍和衰老的研究.
主要成果:
- 对于模拟 (1.17 mm/1.23° vs. 6.09 mm/12.90°转换/旋转误差) 和真实ASL图像 (减少了MSE/L1/DSSIM/总误差18.07%/19.02%/0.04%/29.59%),RNA显示的登记精度优于SPM.
- 与SPM相比,RNA实现了4.4倍更快的处理速度 (0.50秒比2.21秒).
- 经过训练的RNA在不同的扫描仪,分辨率和人群 (健康和患病) 中得到了很好的泛化.
结论:
- 在ASL perfusion fMRI注册的准确性,速度和概括性方面,RNA方法显著优于基于代的SPM.
- ARN提供了一种强大而高效的解决方案,用于记录低SNR的fMRI数据,这对于各种神经成像应用至关重要.
- 这种基于CNN的方法推进了用于低SNRfMRI研究的医疗图像分析领域.
相关概念视频
Magnetic Resonance Imaging
5.2K
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...
5.2K
Imaging Studies for Cardiovascular System IV: CMRI
61
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,...
61


