AI and Neurological Rare & Neuroimmune Diseases ── Multiple sclerosis ── 2026-11-19
Multiple sclerosis: treatment, trials and AI
- Abstract
Ex vivo 9.4T T2*-weighted MRI (75 µm isotropic, magnitude and phase) of human spinal cord samples from 26 donors (18 multiple sclerosis, 4 progressive multifocal leukoencephalopathy, 2 cerebrovascular disease, 2 amyotrophic lateral sclerosis), organized in BIDS. Derivatives include sparse 2D manual segmentations of spinal cord, gray matter and lesions (derivatives/labels_2d), dense 3D pseudo-labels predicted slice-wise by a 2D model (derivatives/pseudo_labels_3d), and one dense manually verified 3D label (derivatives/labels_3d). This dataset accompanies Hoareau et al., "Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data", Machine Learning for Biomedical Imaging (MELBA). Code and models: https://github.com/ivadomed/model_seg_sc-gm-lesion_human_ms_exvivo_t2star
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-11-17, retrieved 2026-11-19; not the official Clarivate IF)Reference: [No authors listed]. Ex vivo 9.4T T2*-weighted MRI of the human spinal cord with spinal cord, gray matter and lesion segmentations (MS, PML, ALS, CVD). Borealis. [Epub ahead of print]. doi:10.5683/sp4/p9zciw.Checked: Abstract only