Ouellette, Russell

Background/Objectives: Characterizing spinal cord multiple sclerosis (MS) lesions in MRI is critical for diagnosis, monitoring, and treatment evaluation. However, current automated approaches for lesion detection and segmentation are typically designed for specific MRI contrasts or acquisition sites, limiting their generalizability in real-world clinical settings where imaging protocols vary widely. This work proposes a robust multi-site, multi-contrast segmentation framework for spinal cord lesions. Methods: The segmentation model was trained and evaluated on a large-scale dataset comprising 4428 annotated images from 1849 persons with MS across 23 imaging centers, encompassing six MRI contrasts (T1w, T2w, T2*w, PSIR, STIR, and UNIT1) acquired at 1.5 tesla (T), 3 T, and 7 T. Results: Likert-type assessment performed by neuroradiologist ratings demonstrated superior generalization of the model compared to existing contrast-specific pipelines ( p < 0.01). Additional experiments evaluated robustness across spinal levels, acquisition resolutions, binarization thresholds, and quantitative evaluation on external labeled datasets. Conclusions: The proposed model can achieve accurate and reliable spinal cord MS lesion segmentation across heterogeneous MRI data, addressing a key barrier to clinical translation. The model is available in the Spinal Cord Toolbox v7.2 and higher. Code repository: https://github.com/ivadomed/seg-sc-ms-lesion-multicontrast

Abstract Objective This study was undertaken to provide a comprehensive review of neuroimaging characteristics and corresponding clinical phenotypes of autoimmune glial fibrillary acidic protein astrocytopathy (GFAP‐A), a rare but severe neuroinflammatory disorder, to facilitate early diagnosis and appropriate treatment. Methods A PRISMA (Preferred Reporting Items for Systematic Reviews and Meta‐Analysis)‐conforming systematic review and meta‐analysis was performed on all available data from January 2016 to June 2023. Clinical and neuroimaging phenotypes were extracted for both adult and paediatric forms. Results A total of 93 studies with 681 cases (55% males; median age = 46, range = 1–103 years) were included. Of these, 13 studies with a total of 535 cases were eligible for the meta‐analysis. Clinically, GFAP‐A was often preceded by a viral prodromal state (45% of cases) and manifested as meningitis, encephalitis, and/or myelitis. The most common symptoms were headache, fever, and movement disturbances. Coexisting autoantibodies (45%) and neoplasms (18%) were relatively frequent. Corticosteroid treatment resulted in partial/complete remission in a majority of cases (83%). Neuroimaging often revealed T2/fluid‐attenuated inversion recovery (FLAIR) hyperintensities (74%) as well as perivascular (45%) and/or leptomeningeal (30%) enhancement. Spinal cord abnormalities were also frequent (49%), most commonly manifesting as longitudinally extensive myelitis. There were 88 paediatric cases; they had less prominent neuroimaging findings with lower frequencies of both T2/FLAIR hyperintensities (38%) and contrast enhancement (19%). Conclusions This systematic review and meta‐analysis provide high‐level evidence for clinical and imaging phenotypes of GFAP‐A, which will benefit the identification and clinical workup of suspected cases. Differential diagnostic cues to distinguish GFAP‐A from common clinical and imaging mimics are provided as well as suitable magnetic resonance imaging protocol recommendations.