In vivo microstructural heterogeneity of white matter and cognitive correlates in aging using tissue compositional analysis of diffusion magnetic resonance imaging

Abstract

Background: Age-related cognitive decline is linked to changes in the brain, particularly the deterioration of white matter (WM) microstructure that accelerates after the age of 60. WM deterioration is associated with mild cognitive impairment and dementia, but the origin and role of white matter signal abnormalities (WMSA) seen in standard MRI remain debated due to their heterogeneity. This study explores the potential of single-shell 3-tissue constrained spherical deconvolution (SS3T-CSD), a novel technique that models diffusion data in terms of gray matter (T_G ), white matter (T_w ), and cerebrospinal fluid (T_C ), to differentiate WMSA from normal-appearing white matter and better understand the interplay between changes in WM microstructure and decline in cognition.

Methods: A total of 189 individuals from the GENIC cohort were included. MRI data, including T1-weighted and diffusion images, were obtained. Preprocessing steps were performed on the diffusion MRI data, followed by the SS3T-CSD. WMSA were segmented using FreeSurfer. Statistical analyses were conducted to assess the association between age, WMSA volume, 3-tissue signal fractions (T_w , T_G , and T_C ), and neuropsychological variables.

Results: Participants above 60 years old showed worse cognitive performance and processing speed compared to those below 60 (p < .001). Age was negatively associated with T_w in normal-appearing white matter (p < .001) and positively associated with T_G in both WMSA (p < .01) and normal-appearing white matter (p < .001). Age was also significantly associated with WMSA volume (p < .001). Higher processing speed was associated with lower T_w and higher T_G , in normal-appearing white matter (p < .01 and p < .001, respectively), as well as increased WMSA volume (p < .001). Similarly, lower MMSE scores correlated with lower T_w and higher T_G in normal-appearing white matter (p < .05). High cholesterol and hypertension were associated with higher WMSA volume (p < .05).

Conclusion: The microstructural heterogeneity within normal-appearing white matter and WMSA is associated with increasing age and cognitive variation, in cognitively unimpaired individuals. Furthermore, the 3-tissue signal fractions are more specific to potential white matter alterations than conventional MRI measures such as WMSA volume. These findings also support the view that the WMSA volumes may be more influenced by vascular risk factors than the 3-tissue metrics. Finally, the 3-tissue metrics were able to capture associations with cognitive tests and therefore capable of capturing subtle pathological changes in the brain in individuals who are still within the normal range of cognitive performance.

Keywords: GENIC; SS3T-CSD; WMSA; aging; diffusion.

FIGURE 1

Flow chart summarizing the key processing steps of the single‐shell 3‐tissue constrained spherical deconvolution (SS3T‐CSD) and T1‐weighted (T1w) pipelines. T1w: Segmentation of white matter signal abnormalities (WMSA) was performed with FreeSurfer. Once segmented, the WMSA masks were binarized. A normal‐appearing white matter mask was also computed by subtracting the WMSA mask from the entire white matter (WM) mask. DWI: Single‐shell, b = 1000, 31 gradient directions diffusion data were processed using a combination of commands in the MRtrix3 package as well as the FMRIB Software Library. Basic processing included points 1–5. A fully automated unsupervised method to obtain 3‐tissue response function estimation for tissue compartments WM‐GM‐CSF was used. WM fiber orientation distributions (FODs), as well as gray matter (GM) and cerebrospinal fluid (CSF) compartments, were then computed using a SS3T‐CSD. Spatial alignment of the diffusion and T1w data was performed for each participant. Finally, we normalized the tissue fractions to sum to unity to extract the 3‐tissue signal fractions T_w, T_G, and T_C within WMSA and normal‐appearing white matter (NAWM).

FIGURE 2

Scatter plots for Spearman correlation analysis of age with the relative 3‐tissue signal fractions (T_w, T_G, and T_C) within white matter signal abnormalities (WMSA) and normal‐appearing white matter as well as WMSA volume. WMSA refers to white matter signal abnormalities; NAWM refers to normal‐appearing white matter; T_w, T_G, and T_C mean tissue fractions of the white matter, gray matter, and cerebrospinal fluid (CSF), respectively. Results with uncorrected p < .05 are shown. Significant results after FDR are in bold red. Adjusted thresholds with FDR are p = .028.

FIGURE 3

Scatter plots for Spearman correlation analysis of Pc Vienna System Reaction time (PCv RT) with the relative 3‐tissue signal fractions (T_w, T_G, and T_C) within white matter signal abnormalities (WMSA) and normal‐appearing white matter as well as WMSA volume. PcV RT, Personal computer Vienna Reaction time; WMSA refers to white matter signal abnormalities; NAWM refers to normal‐appearing white matter; T_w, T_G, and T_C mean tissue fractions of the white matter, gray matter, and cerebrospinal fluid (CSF), respectively. Results with uncorrected p < .05 are shown. Significant results after false discovery rate (FDR) are in bold red. The adjusted threshold with FDR is p = .01. Color code: red circle refers to participants under 60 years old, and blue triangle refers to participants older than 60. WMSA volume is in mm³.

FIGURE 4

Scatter plots for Spearman correlation analysis of MMSE with the relative 3‐tissue signal fractions (T_w, T_G, and T_C) within white matter signal abnormalities (WMSA) and normal‐appearing white matter as well as WMSA volume. Mini‐mental state examination (MMSE); WMSA refers to white matter signal abnormalities; NAWM refers to normal‐appearing white matter; T_w, T_G, and T_C mean tissue fractions of the white matter, gray matter, and cerebrospinal fluid (CSF), respectively. Results with uncorrected p < .05 are shown. Significant results after false discovery rate (FDR) are in bold red. The adjusted threshold with FDR is p = .01. Color code: red circle refers to participants under 60 years old, and blue triangle refers to participants older than 60.