Lifespan reference curves for harmonizing multi-site regional brain white matter metrics from diffusion MRI

Abstract

Age-related white matter (WM) microstructure maturation and decline occur throughout the human lifespan, complementing the process of gray matter development and degeneration. Here, we create normative lifespan reference curves for global and regional WM microstructure by harmonizing diffusion MRI (dMRI)-derived data from ten public datasets (N = 40,898 subjects; age: 3-95 years; 47.6% male). We tested three harmonization methods on regional diffusion tensor imaging (DTI) based fractional anisotropy (FA), a metric of WM microstructure, extracted using the ENIGMA-DTI pipeline. ComBat-GAM harmonization provided multi-study trajectories most consistent with known WM maturation peaks. Lifespan FA reference curves were validated with test-retest data and used to assess the effect of the ApoE4 risk factor for dementia in WM across the lifespan. We found significant associations between ApoE4 and FA in WM regions associated with neurodegenerative disease even in healthy individuals across the lifespan, with regional age-by-genotype interactions. Our lifespan reference curves and tools to harmonize new dMRI data to the curves are publicly available as eHarmonize (https://github.com/ahzhu/eharmonize).

Figure 1.

(A) After harmonization using different methods, average FA in the full WM skeleton is plotted against age and colored by study. Age-binned boxplots of (B) unharmonized data and (C) data harmonized using ComBat-GAM show the median global FA were quite different between protocols pre-harmonization and were more similar post-harmonization.

Figure 2.

(A) Iteration-specific reference curves of the global FA measure as created by iterative subsampling of ~200 participants from each study and ComBat-GAM harmonization are displayed (25 iterations; mean in black). (B) Sex-specific centile curves derived from the results of iterative subsampling harmonization make up the final lifespan reference curve. (C) After applying our framework (eHarmonize) to held-out evaluation datasets, the harmonized datasets fall in line with the global FA lifespan reference curve.

Figure 3.

For most ROIs, the shift parameter extracted from the ComBat-GAM model was significantly correlated with voxel volume. The negative correlation between the global FA shift parameter and voxel volume is shown here (r = −0.60; p < 0.001).

Figure 4.

Age associations, residualized by sex, age-by-sex, and age, are plotted for the (A) CGH and (B) FXST. In the CGH, E4 carriers had significantly lower FA compared to their E3E3 counterparts. In the FXST, the FA of E4 carriers was higher at younger ages but after approximately age 55 years, dropped below that of non-carriers in older ages. A comparison of protocols in the (C) ADNI3-S127 and (D) QTIM datasets showed that harmonization does not converge the results of the same subjects acquired with different protocols. Each scatter point reflects the association (standardized beta) between ApoE4 and an ROI, corrected for age, sex, age-by-sex, and age.

Figure 5.

Standardized betas for age associations with each WM ROI either pre-harmonization (x-axis) or post-harmonization (y-axis). Harmonization was either performed by (A) applying baseline parameters to follow-up data, or (B) modeling the ComBat parameters for each time point separately.

Figure 6.

(A) The eHarmonize command line interface comes with two subcommands: harmonize-fa for harmonizing data from a new site, and apply-harmonization for applying an existing harmonization model to a known site. (B) The ENIGMA-DTI template with the skeleton and ROIs overlaid. (C) QC output showing data before and after harmonization in relation to the reference curve, shown in gray.