Multiple sclerosis : clinical and laboratory research
-
Randomized Controlled Trial
Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study.
To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients. ⋯ The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.
-
Investigating the degeneration of specific thalamic nuclei in multiple sclerosis (MS) remains challenging. ⋯ WMn-MPRAGE and automatic thalamic segmentation can highlight thalamic MS lesions and measure patterns of focal thalamic atrophy.
-
Functional magnetic resonance imaging (fMRI) correlates of cognitive deficits have not been thoroughly studied in patients with neuromyelitis optica spectrum disorders (NMOSDs). ⋯ Cognitive-network reorganization occurs in NMOSD. Clinico-imaging correlations suggest an adaptive role of increased RS FC. Conversely, reduced RS FC seems to be a maladaptive mechanism associated with a worse cognitive performance.
-
Misdiagnosis is common in multiple sclerosis (MS) as a proportion of patients present with atypical clinical/magnetic resonance imaging (MRI) findings. The central vein sign has the potential to be a non-invasive, MS-specific biomarker. ⋯ The central vein sign assessed with a clinically available T2* scan can successfully diagnose MS in cases of diagnostic uncertainty. The central vein sign should be considered as a diagnostic biomarker in MS.