Pantoni L, Marzi C, Poggesi A, et al. - Researchers sought to assess the utility of fractal dimension (FD) values of cerebral white matter (WM FD) and cortical gray matter (GM FD) as structural predictors of cognitive performance in patients with small vessel disease (SVD) and mild cognitive impairment (MCI). FD can be computed from high-resolution T₁-weighted images. Sixty-four patients (mean age ± standard deviation, 74.6 ± 6.9, education 7.9 ± 4.2 years, 53% males) with SVD and MCI, and a control group of 24 healthy individuals (mean age ± standard deviation, 72.3 ± 4.4 years, 50% males) were included. A machine learning strategy was employed that was based on LASSO (least absolute shrinkage and selection operator) regression applied on several neuroimaging features in a nested cross-validation loop. Outcomes support the utility of a machine learning approach in SVD using standard and advanced neuroimaging features. As per outcomes, SVD patients with MCI display altered WM FD. A consistent decrease in white matter complexity was identified as predictive of worse cognitive performance. Findings support the possible value of FD as a new marker of white matter damage in SVD.