White matter correlates of sensorimotor synchronization in persistent developmental stuttering

Abstract

Introduction: Individuals with persistent developmental stuttering display deficits in aligning motor actions to external cues (i.e., sensorimotor synchronization). Diffusion imaging studies point to stuttering-associated differences in dorsal, not ventral, white matter pathways, and in the cerebellar peduncles. Here, we studied microstructural white matter differences between adults who stutter (AWS) and fluent speakers using two complementary approaches to: (a) assess previously reported group differences in white matter diffusivity, and (b) evaluate the relationship between white matter diffusivity and sensorimotor synchronization in each group.

Methods: Participants completed a sensorimotor synchronization task and a diffusion MRI scan. We identified the cerebellar peduncles and major dorsal- and ventral-stream language pathways in each individual and assessed correlations between sensorimotor synchronization and diffusion measures along the tracts.

Results: The results demonstrated group differences in dorsal, not ventral, language tracts, in alignment with prior reports. Specifically, AWS had significantly lower fractional anisotropy (FA) in the left arcuate fasciculus, and significantly higher mean diffusivity (MD) in the bilateral frontal aslant tract compared to fluent speakers, while no significant group difference was detected in the inferior fronto-occipital fasciculus. We also found significant group differences in both FA and MD of the left middle cerebellar peduncle. Comparing patterns of association with sensorimotor synchronization revealed a novel double dissociation: MD within the left inferior cerebellar peduncle was significantly correlated with mean asynchrony in AWS but not in fluent speakers, while FA within the left arcuate fasciculus was significantly correlated with mean asynchrony in fluent speakers, but not in AWS.

Conclusions: Our results support the view that stuttering involves altered connectivity in dorsal tracts and that AWS may rely more heavily on cerebellar tracts to process timing information. Evaluating microstructural associations with sensitive behavioral measures provides a powerful tool for discovering additional functional differences in the underlying connectivity in AWS.

Keywords: Cerebellum; Diffusion MRI; Dorsal pathways; Sensorimotor synchronization; Tractography; persistent developmental stuttering.

Figure 1.. Tracts of interest.

Shown are the left (a) and right (b) tracts of interest identified in a single participant (S43, fluent speaker, female, 19y), overlaid on a midsagittal T1 image of the same individual. The dorsal tracts identified are the arcuate fasciculus (green) and the frontal aslant tract (FAT; light blue). The ventral tract identified is the inferior fronto-occipital fasciculus (IFOF; orange). The cerebellar tracts identified are the superior cerebellar peduncle (SCP; purple), middle cerebellar peduncle (MCP; magenta), and the inferior cerebellar peduncle (ICP; yellow).

Figure 2.. Testing Hypothesis 1: Reduced FA in the bilateral arcuate fasciculus of AWS.

(a, d): The left (a) and right (d) arcuate fasciculi are identified in a single participant (S31, fluent speaker, female, 31y), overlaid on a midsagittal T1 image of the same individual. Shaded region in (a) indicate the location of the significant cluster of nodes. (b, e): Bar graphs show the group average tract-FA of the left (b) and right (e) arcuate fasciculus in AWS (red) and fluent speakers (blue). Error bars denote ±1 standard error of the mean. Asterisk denotes a significant group difference (p=.014, FDR controlled at 5% for 2 comparisons). (c, f): FA profiles along the left arcuate fasciculus (c) and the right arcuate fasciculus (f) are shown in AWS (red) and fluent speakers (blue), with colored dotted lines indicating ±1 standard error of the mean. Asterisk denotes a significant group difference (p<.05, FWE corrected over 100 nodes). AWS – red, fluent speakers – blue.

Figure 3.. Testing Hypothesis 2: Elevated MD in the bilateral frontal aslant tract of AWS.

(a, d): The left (a) and right (d) FAT are identified in a single participant (S20, AWS, female, 18y), overlaid on a coronal T1 image of the same individual. Shaded region in (d) indicate the location of the significant cluster of nodes. (b, e): Bar graphs show the group average tract-MD of the left (b) and right (e) FAT in AWS (red) and fluent speakers (blue). Error bars denote ±1 standard error of the mean. Asterisk denotes a significant group difference (p=.04, FDR controlled at 5% for 2 comparisons). (c, f): MD profiles along the left (c) and right (f) FAT are shown in AWS (red) and fluent speakers (blue), with colored dotted lines indicating ±1 standard error of the mean. Asterisk denotes a significant group difference (p<.05, FWE correction over 100 nodes). AWS – red, fluent speakers – blue.

Figure 4.. Group comparison of the bilateral inferior fronto-occipital fasciculus (IFOF).

(a, d): The left (a) and right (d) IFOF are identified in a single participant (S12, fluent speaker, female, 23y), overlaid on a midsagittal T1 image of the same individual. (b, e): Bar graphs show the group average tract-FA of the left (b) and right (e) IFOF in AWS (red) and fluent speakers (blue). Error bars denote ±1 standard error of the mean. (c, f): FA profiles along the left (c) and right (f) IFOF are shown in AWS (red) and fluent speakers (blue), with colored dotted lines indicating ±1 standard error of the mean. AWS – red, fluent speakers – blue.

Figure 5.. Testing Hypothesis 3: Reduced FA in the bilateral cerebellar peduncles (CPs) of AWS.

The results are shown for the left CPs (left column) and the right CPs (right column). a) The left and right SCP (purple), MCP (magenta) and ICP (yellow) are identified in a single participant (S43, fluent speaker, female, 19y), overlaid on a midsagittal T1 image of the same individual. Shaded region indicate the location of the significant cluster of nodes. b) Bar graphs show the group average tract-FA in AWS (red) and fluent speakers (blue). Error bars denote ±1 standard error of the mean. Asterisk denotes a significant group difference (p=.004, FDR controlled at 5% for 6 comparisons). (c-e): FA profiles along the bilateral SCP (c), MCP (d) and ICP (e) are shown in AWS (red) and fluent speakers (blue), with colored dotted lines indicating ±1 standard error of the mean. Asterisk denotes a significant group difference (p<.05, FWE corrected over 30 nodes). AWS – red, fluent speakers – blue.

Figure 6.. Mean asynchrony is correlated with FA of the left arcuate fasciculus among fluent speakers, but not among adults who stutter.

(a) Spearman’s r values calculated in each node along the core of the tract in fluent speakers (N=14). (b) Individual tract-FA values of the left arcuate fasciculus are plotted against individual mean asynchrony values in AWS (red) and fluent speakers (blue). A significant correlation is detected in fluent speakers (r=.62, p=.025, uncorrected) but not in AWS (r= −.005, p=.99). (c) Distributions of correlation coefficients were generated using bootstrap analysis by drawing repeated samples from the AWS group (red) and fluent speakers (blue). This analysis revealed that the probability for observing the correlation coefficient of AWS under the distribution of the fluent speakers is p=.013. AWS – red, fluent speakers – blue.

Figure 7.. Mean asynchrony is correlated with MD in the left ICP among adults who stutter, but not among fluent speakers.

(a) The correlation between MD and mean asynchrony was assessed by calculating Spearman’s r values in each node along the core of the tract in AWS (N=13). A significant correlation is observed in nodes 19–23, denoted by the black arrow (p<.05, FWE corrected for 30 nodes). No significant cluster was observed in fluent speakers (not shown). (b) The mean MD value drawn from the significant cluster of nodes observed in AWS (see a) is plotted against the mean asynchrony in AWS (red) and fluent speakers (blue). (c) Distributions of correlation coefficients were generated using bootstrap analysis by drawing repeated samples from the AWS group (red) and fluent speakers (blue). This analysis revealed that the probability for observing the correlation coefficient of AWS under the distribution of the fluent speakers is p=.003. AWS – red, fluent speakers – blue.