Comparing Harmonization Approaches for Protocol-Related Variability in Multisite Diffusion MRI Data
Liou, K.; Thomopoulos, S. I.; Villalon Reina, J. E.; Yoo, H.; Shuai, Y.; Chehrzadeh, S.; Arani, A.; Borowski, B.; Reid, R. I.; Vemuri, P.; Jack, C. R.; Weiner, M.; Jahanshad, N.; Thompson, P. M.; Nir, T. M.
Show abstract
Diffusion MRI (dMRI) enables assessment of white matter microstructural abnormalities in Alzheimers disease (AD), and multisite datasets enable more robust modeling of non-biological variation that can confound analyses. The Alzheimers Disease Neuroimaging Initiative (ADNI) includes over 10 dMRI protocols, necessitating robust methods to model protocol-related variability when pooling data. Here, we compared three harmonization approaches: (1) mixed-effects models, (2) ComBat-GAM, and (3) eHarmonize, a reference-based lifespan method. We assessed their ability to reduce protocol-related variability in diffusion tensor imaging fractional anisotropy (FA) and mean diffusivity (MD) while preserving associations with cognitive impairment (CI), and amyloid-beta (A{beta}) and tau PET burden in 1,086 ADNI3/4 participants. All approaches yielded more closely aligned FA/MD distributions across protocols. Associations with clinical indicators of CI were highly consistent across approaches, whereas PET associations were less widespread and more variable. Overall, multiple strategies effectively modeled protocol-related variability while preserving AD-related associations.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.