Long-term white matter tract reorganization following prolonged febrile seizures

Abstract

Objective: Diffusion magnetic resonance imaging (MRI) studies have demonstrated acute white matter changes following prolonged febrile seizures (PFS), but their longer-term evolution is unknown. We investigated a population-based cohort to determine white matter diffusion properties 8 years after PFS.

Methods: We used diffusion tensor imaging (DTI) and applied Tract-Based Spatial Statistics for voxel-wise comparison of white matter microstructure between 26 children with PFS and 27 age-matched healthy controls. Age, gender, handedness, and hippocampal volumes were entered as covariates for voxel-wise analysis.

Results: Mean duration between the episode of PFS and follow-up was 8.2 years (range 6.7-9.6). All children were neurologically normal, and had normal conventional neuroimaging. On voxel-wise analysis, compared to controls, the PFS group had (1) increased fractional anisotropy in early maturing central white matter tracts, (2) increased mean and axial diffusivity in several peripheral white matter tracts and late-maturing central white matter tracts, and (3) increased radial diffusivity in peripheral white matter tracts. None of the tracts had reduced fractional anisotropy or diffusivity indices in the PFS group.

Significance: In this homogeneous, population-based sample, we found increased fractional anisotropy in early maturing central white matter tracts and increased mean and axial diffusivity with/without increased radial diffusivity in several late-maturing peripheral white matter tracts 8 years post-PFS. We propose disruption in white matter maturation secondary to seizure-induced axonal injury, with subsequent neuroplasticity and microstructural reorganization as a plausible explanation.

Keywords: Axonal injury; Diffusion tensor imaging; Neuroplasticity; Status epilepticus; White matter.

Figure 1

Flow diagram showing recruitment for the current study and reasons for noninclusion in the TBSS analysis.

Figure 2

Results of whole‐brain TBSS analysis revealed widespread differences between the PFS group and controls in FA, mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) maps. Regions in green represent the mean FA skeleton, and therefore no significant difference between the two groups. Regions in red‐yellow represent significant increases in the PFS group (p < 0.05, FWE corrected).

Figure 3

Illustration depicting the balance between axonal loss and axonal coherence, and their influence on FA. Although increased axonal coherence with modest axonal loss in early‐maturing WM tracts results in FA increase, the increased axonal coherence is counterbalanced by a greater axonal loss in late‐maturing WM tracts with no change in FA.