Introduction Currently, there are no tools that can accurately predict which patients with mild cognitive impairment (MCI) will progress to Alzheimer's disease (AD). Texture analysis uses image processing and statistical methods to identify patterns in voxel intensities that cannot be appreciated by visual inspection. Our main objective was to determine whether MRI texture could be used to predict conversion of MCI to AD. Methods A method of 3-dimensional, whole-brain texture analysis was used to compute texture features from T1-weighted MR images. To assess predictive value, texture changes were compared between MCI converters and nonconverters over a 3-year observation period. A predictive model using texture and clinical factors was used to predict conversion of patients with MCI to AD. This model was then tested on ten randomly selected test groups from the data set. Results Texture features were found to be significantly different between normal controls (n = 225), patients with MCI (n = 382), and patients with AD (n = 183). A subset of the patients with MCI were used to compare between MCI converters (n = 98) and nonconverters (n = 106). A composite model including texture features, APOE -ε4 genotype, Mini-Mental Status Examination score, sex, and hippocampal occupancy resulted in an area under curve of 0.905. Application of the composite model to ten randomly selected test groups (nonconverters = 26, converters = 24) predicted MCI conversion with a mean accuracy of 76.2%. Discussion Early texture changes are detected in patients with MCI who eventually progress to AD dementia. Therefore, whole-brain 3D texture analysis has the potential to predict progression of patients with MCI to AD.

BackgroundWe investigated cerebral degeneration and neurochemistry in patients with amyotrophic lateral sclerosis (ALS) using magnetic resonance spectroscopy (MRS).MethodsWe prospectively studied 65 patients and 43 age-matched healthy controls. Participants were recruited from 4 centers as part of a study in the Canadian ALS Neuroimaging Consortium. All participants underwent single-voxel proton MRS using a protocol standardized across all sites. Metabolites reflecting neuronal integrity (total N-acetyl aspartyl moieties [tNAA]) and gliosis (myo-inositol [Ino]), as well as creatine (Cr) and choline (Cho), were quantified in the midline motor cortex and midline prefrontal cortex. Comparisons were made between patients with ALS and healthy controls. Metabolites were correlated with clinical measures of upper motor neuron dysfunction, disease progression rate, and cognitive performance.ResultsIn the motor cortex, tNAA/Cr, tNAA/Cho, and tNAA/Ino ratios were reduced in the ALS group compared with controls. Group differences in tNAA/Cr and tNAA/Cho in the prefrontal cortex displayed reduced ratios in ALS patients; however, these were not statistically significant. Reduced motor cortex ratios were associated with slower foot tapping rate, whereas only motor tNAA/Ino was associated with finger tapping rate. Disease progression rate was associated with motor tNAA/Cho. Verbal fluency, semantic fluency, and digit span forwards and backwards were associated with prefrontal tNAA/Cr.ConclusionsThis study demonstrates that cerebral degeneration in ALS is more pronounced in the motor than prefrontal cortex, that multicenter MRS studies are feasible, and that motor tNAA/Ino shows promise as a potential biomarker.