De Luca Alberto, Swartenbroekx Tine, Seelaar Harro, van Swieten John, Cetin Karayumak Suheyla, Rathi Yogesh, Pasternak Ofer, Jiskoot Lize, Leemans Alexander
Image Sciences Institute, Center for Image Sciences, University Medical Center Utrecht, Utrecht, the Netherlands.
Department of Neurology and Alzheimer Center, Erasmus MC University Medical Center, Rotterdam, the Netherlands.
Magn Reson Med. 2025 Oct;94(4):1750-1762. doi: 10.1002/mrm.30575. Epub 2025 May 23.
Diffusion MRI (dMRI) data typically suffer of significant cross-site variability, which prevents naively performing pooled analyses. To attenuate cross-site variability, harmonization methods such as the rotational invariant spherical harmonics (RISH) have been introduced to harmonize the dMRI data at the signal level. A common requirement of the RISH method is the availability of healthy individuals who are matched at the group level, which may not always be readily available, particularly retrospectively. In this work, we propose a framework to harmonize dMRI without matched training groups.
Our framework learns harmonization features while controlling for potential covariates using a voxel-based generalized linear model (GLM). RISH-GLM allows us to simultaneously harmonize data from any number of sites while also accounting for covariates of interest, thus not requiring matched training subjects. Additionally, RISH-GLM can harmonize data from multiple sites in a single step, whereas RISH is performed for each site independently.
We considered data of training subjects from retrospective cohorts acquired with three different scanners and performed three harmonization experiments of increasing complexity. First, we demonstrate that RISH-GLM is equivalent to conventional RISH when trained with data of matched training subjects. Second, we demonstrate that RISH-GLM can effectively learn harmonization with two groups of highly unmatched subjects. Third, we evaluate the ability of RISH-GLM to simultaneously harmonize data from three different sites.
RISH-GLM can learn cross-site harmonization both from matched and unmatched groups of training subjects and can effectively be used to harmonize data of multiple sites in one single step.
扩散磁共振成像（dMRI）数据通常存在显著的跨站点变异性，这使得简单地进行汇总分析变得困难。为了减弱跨站点变异性，已引入诸如旋转不变球谐函数（RISH）等归一化方法在信号层面上对dMRI数据进行归一化。RISH方法的一个常见要求是在组水平上匹配的健康个体的可用性，而这可能并不总是容易获得的，特别是在回顾性研究中。在这项工作中，我们提出了一个在没有匹配训练组的情况下对dMRI进行归一化的框架。
我们的框架在使用基于体素的广义线性模型（GLM）控制潜在协变量的同时学习归一化特征。RISH-GLM使我们能够同时对来自任意数量站点的数据进行归一化，同时还能考虑感兴趣的协变量，因此不需要匹配的训练对象。此外，RISH-GLM可以在单个步骤中对来自多个站点的数据进行归一化，而RISH是对每个站点独立进行的。
我们考虑了来自使用三种不同扫描仪采集的回顾性队列中训练对象的数据，并进行了三个复杂度不断增加的归一化实验。首先，我们证明当使用匹配训练对象的数据进行训练时，RISH-GLM等同于传统的RISH。其次，我们证明RISH-GLM可以有效地学习两组高度不匹配对象之间的归一化。第三，我们评估了RISH-GLM同时对来自三个不同站点的数据进行归一化的能力。
RISH-GLM可以从匹配和不匹配的训练对象组中学习跨站点归一化，并且可以有效地用于在单个步骤中对多个站点的数据进行归一化。
