Search

Background: Mild Cognitive Impairment (MCI) is a heterogeneous condition characterised by cognitive changes that do not affect everyday functioning and may represent a predementia phase. Research on the neuroanatomical correlates of cognitive tests used to diagnose MCI is heterogeneous and has mainly focused on elderly populations of patients with MCI, usually well above the age of 65. However, the effect of ageing on brain structure is known to be substantial and to affect brain-behaviour associations in older people. We explored the brain correlates of different cognitive tests in a group of young-onset MCI (i.e., with symptoms onset before the age of 65) to minimise the effect of ageing on brain-behaviour associations. Methods: Patients with a clinical diagnosis of young-onset MCI underwent extensive cognitive assessment and multimodal Magnetic Resonance Imaging (MRI) including high-resolution T1-weighted and Diffusion Tensor Imaging (DTI) sequences. Their scores on cognitive tests were related to measures of grey matter (GM) density and white matter (WM) integrity using, respectively, Voxel Based Morphometry (VBM) and Tract-Based Spatial Statistics (TBSS). Results: 104 young-onset MCI were recruited. VBM and TBSS whole-brain correlational analyses showed that between-subject variability in cognitive performance was significantly associated with regional variability in GM density and WM integrity. While associations between cognitive scores and focal GM density in our young-onset MCI group reflected the well-known lateralization of verbal and visuo-spatial abilities on the left and right hemispheres respectively, the associations between cognitive scores and WM microstructural integrity were widespread and diffusely involved most of the WM tracts in both hemispheres. Conclusions: We investigated the structural neuroanatomical correlates of cognitive tests in young-onset MCI in order to minimise the effect of ageing on brain-behaviour associations. [ABSTRACT FROM AUTHOR]

Research on segmentation of the hippocampus in magnetic resonance images through deep learning convolutional neural networks (CNNs) shows promising results, suggesting that these methods can identify small structural abnormalities of the hippocampus, which are among the earliest and most frequent brain changes associated with Alzheimer disease (AD). However, CNNs typically achieve the highest accuracy on datasets acquired from the same domain as the training dataset. Transfer learning allows domain adaptation through further training on a limited dataset. In this study, we applied transfer learning on a network called spatial warping network segmentation (SWANS), developed and trained in a previous study. We used MR images of patients with clinical diagnoses of mild cognitive impairment (MCI) and AD, segmented by two different raters. By using transfer learning techniques, we developed four new models, using different training methods. Testing was performed using 26% of the original dataset, which was excluded from training as a hold‐out test set. In addition, 10% of the overall training dataset was used as a hold‐out validation set. Results showed that all the new models achieved better hippocampal segmentation quality than the baseline SWANS model (ps <.001), with high similarity to the manual segmentations (mean dice [best model] = 0.878 ± 0.003). The best model was chosen based on visual assessment and volume percentage error (VPE). The increased precision in estimating hippocampal volumes allows the detection of small hippocampal abnormalities already present in the MCI phase (SD = [3.9 ± 0.6]%), which may be crucial for early diagnosis. [ABSTRACT FROM AUTHOR]

The article discusses research on the association between concentrations of selenium species in cerebrospinal fluid (CSF) and hippocampal volume in individuals with mild cognitive impairment (MCI). Data shows the sociodemographic characteristics of participants and the CSF levels of organic selenoprotein P species compared with inorganic selenate and selenites species. Results revealed imprecise association of hippocampal volume with selenocysteine and selenium-dependent glutathione peroxidase.