Guan Hao, Liu Siyuan, Lin Weili, Yap Pew-Thian, Liu Mingxia
Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Marine Engineering College, Dalian Maritime University, Dalian 116026, China.
Mach Learn Med Imaging. 2022 Sep;13583:201-209. doi: 10.1007/978-3-031-21014-3_21. Epub 2022 Dec 16.
Pooling structural magnetic resonance imaging (MRI) data from different imaging sites helps increase sample size to facilitate machine learning based neuroimage analysis, but usually suffers from significant cross-site and/or cross-scanner data heterogeneity. Existing studies often focus on reducing cross-site and/or cross-scanner heterogeneity at handcrafted feature level targeting specific tasks (e.g., classification or segmentation), limiting their adaptability in clinical practice. Research on image-level MRI harmonization targeting a broad range of applications is very limited. In this paper, we develop a spectrum swapping based image-level MRI harmonization (SSIMH) framework. Different from previous work, our method focuses on alleviating cross-scanner heterogeneity at . We first construct to explore the influences of different frequency components on MRI harmonization. We then utilize a method for the harmonization of raw MRIs acquired by different scanners. Our method does not rely on complex model training, and can be directly applied to fast real-time MRI harmonization. Experimental results on T1- and T2-weighted MRIs of phantom subjects acquired by using different scanners from the public ABCD dataset suggest the effectiveness of our method in structural MRI harmonization at the image level.
汇集来自不同成像站点的结构磁共振成像（MRI）数据有助于增加样本量，以促进基于机器学习的神经影像分析，但通常会受到显著的跨站点和/或跨扫描仪数据异质性的影响。现有研究通常侧重于在针对特定任务（例如分类或分割）的手工特征级别上减少跨站点和/或跨扫描仪的异质性，这限制了它们在临床实践中的适应性。针对广泛应用的图像级MRI协调研究非常有限。在本文中，我们开发了一种基于频谱交换的图像级MRI协调（SSIMH）框架。与先前的工作不同，我们的方法侧重于减轻……处的跨扫描仪异质性。我们首先构建……以探索不同频率成分对MRI协调的影响。然后，我们利用一种……方法对不同扫描仪采集的原始MRI进行协调。我们的方法不依赖于复杂的模型训练，并且可以直接应用于快速实时MRI协调。使用来自公共ABCD数据集的不同扫描仪获取的体模受试者的T1加权和T2加权MRI的实验结果表明，我们的方法在图像级结构MRI协调方面是有效的。
