Diffusion tensor MRI tractography and cognitive impairment in multiple sclerosis.

OBJECTIVE: To assess the correlation between cognitive impairment and overall vs regional CNS damage, quantified using conventional and diffusion tensor (DT) MRI tractography in multiple sclerosis (MS). METHODS: Brain dual-echo, T1-weighted, and DT MRI data were acquired from 82 patients with MS. DT tractography was used to produce maps of white matter (WM) tracts involved in cognition. The sensory thalamocortical projections and optic radiations were studied as "control" WM tracts. The contribution of global brain damage (T2 lesion volume, normalized brain volume, gray matter [GM] volume, WM volume, DT MRI measures of normal-appearing WM and GM damage) and damage to selected WM tracts to overall cognitive impairment and to impairment at individual neuropsychological tests was assessed using a random forest (RF) analysis. RESULTS: Thirty-three patients had cognitive impairment. The majority of MRI measures differed significantly between cognitively impaired and cognitively preserved (CP) patients. Significant correlations were found between performance in the majority of neuropsychological tests and global or regional brain damage (r ranging from -0.60 to 0.57). The RF analysis showed a high performance in classifying cognitively impaired vs CP patients, with a classification (C)-index = 76.8, as well as in classifying patients' impairment in individual neuropsychological tests (C-index between 75.6% and 86.6%). Measures of lesional damage in cognitive-related tracts, rather than measures of normal-appearing WM damage in the same tracts or global brain/WM/GM damage, resulted in the highest classification accuracy. CONCLUSIONS: Lesions in strategic brain WM tracts contribute to cognitive impairment in MS through a multisystem disconnection syndrome.

Overcoming the clinical-MR imaging paradox of multiple sclerosis: MR imaging data assessed with a random forest approach.

BACKGROUND AND PURPOSE: In MS, the relation between clinical and MR imaging measures is still suboptimal. We assessed the correlation of disability and specific impairment of the clinical functional system with overall and regional CNS damage in a large cohort of patients with MS with different clinical phenotypes by using a random forest approach. MATERIALS AND METHODS: Brain conventional MR imaging and DTI were performed in 172 patients with MS and 46 controls. Cervical cord MR imaging was performed in a subgroup of subjects. To evaluate whether MR imaging measures were able to correctly classify impairment in specific clinical domains, we performed a random forest analysis. RESULTS: Between-group differences were found for most of the MR imaging variables, which correlated significantly with clinical measures (r ranging from -0.57 to 0.55). The random forest analysis showed a high performance in identifying impaired versus unimpaired patients, with a global error between 7% (pyramidal functional system) and 31% (Ambulation Index) in the different outcomes considered. When considering the performance in the unimpaired and impaired groups, the random forest analysis showed a high performance in identifying patients with impaired sensory, cerebellar, and brain stem functions (error below 10%), while it performed poorly in defining impairment of visual and mental systems (error of 91% and 70%, respectively). In analyses with a good level of classification, for most functional systems, damage of the WM fiber bundles subserving their function, measured by using DTI tractography, had the highest classification power. CONCLUSIONS: Random forest analysis, especially if applied to DTI tractography data, is a valuable approach, which might contribute to overcoming the MS clinical-MR imaging paradox.