“…Data harmonization is a prerequisite step in neuroimaging studies with data from multiple sites (Shinohara et al, 2017). Several methods have been developed to harmonize data from different sites, including ComBat and its variants, normative modelling, as well as deep learning based algorithms that transfer the data from different sites into a common, comparable space (Fortin et al, 2017; Fortin et al, 2018; Yu et al, 2018; Dewey et al, 2019; Kia et al, 2020; Moyer et al, 2020; Bayer et al, 2021; Liu et al, 2021; Zuo et al, 2021; Rutherford et al, 2022; Sun et al, 2022). Particularly, ComBat and its variants have been successfully applied to a variety of neuroimaging studies to harmonize diffusion tensor imaging measures, cortical thickness, regional volume measures, and functional connectivity measures (Fortin et al, 2017; Fortin et al, 2018; Yu et al, 2018).…”