Cross‐site harmonization of diffusion MRI data without matched training subjects

• Published in: Magnetic resonance in medicine Vol. 94; no. 4; pp. 1750 - 1762
• Main Authors: De Luca, Alberto, Swartenbroekx, Tine, Seelaar, Harro, van Swieten, John, Cetin Karayumak, Suheyla, Rathi, Yogesh, Pasternak, Ofer, Jiskoot, Lize, Leemans, Alexander
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.10.2025; John Wiley and Sons Inc
• Subjects: Adult; Algorithms; Availability; brain; Brain - diagnostic imaging; Computer Processing and Modeling; Diffusion Magnetic Resonance Imaging - methods; diffusion mri; diffusion tensor imaging; Female; Generalized linear models; harmonization; Humans; Image Processing, Computer-Assisted - methods; Linear Models; Magnetic resonance imaging; Male; Reproducibility of Results; Retrospective Studies; Spherical harmonics; Statistical models; diffusion tensor imaging; diffusion mri; brain; harmonization
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.30575

Purpose 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. Methods 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. Results 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. Conclusion 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.