The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework — robust to variability in both image parameters and clinical condition — for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1,042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n=30). Data spanned three contrasts (T1-, T2-, and T2*-weighted) for a total of 1,943 volumes and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p≤0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of −15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.

Objective This study was undertaken to investigate the gut microbiome in progressive multiple sclerosis (MS) and how it relates to clinical disease. Methods We sequenced the microbiota from healthy controls and relapsing–remitting MS (RRMS) and progressive MS patients and correlated the levels of bacteria with clinical features of disease, including Expanded Disability Status Scale (EDSS), quality of life, and brain magnetic resonance imaging lesions/atrophy. We colonized mice with MS‐derived Akkermansia and induced experimental autoimmune encephalomyelitis (EAE). Results Microbiota β‐diversity differed between MS patients and controls but did not differ between RRMS and progressive MS or differ based on disease‐modifying therapies. Disease status had the greatest effect on the microbiome β‐diversity, followed by body mass index, race, and sex. In both progressive MS and RRMS, we found increased Clostridium bolteae, Ruthenibacterium lactatiformans, and Akkermansia and decreased Blautia wexlerae, Dorea formicigenerans, and Erysipelotrichaceae CCMM. Unique to progressive MS, we found elevated Enterobacteriaceae and Clostridium g24 FCEY and decreased Blautia and Agathobaculum. Several Clostridium species were associated with higher EDSS and fatigue scores. Contrary to the view that elevated Akkermansia in MS has a detrimental role, we found that Akkermansia was linked to lower disability, suggesting a beneficial role. Consistent with this, we found that Akkermansia isolated from MS patients ameliorated EAE, which was linked to a reduction in RORγt+ and IL‐17–producing γδ T cells. Interpretation Whereas some microbiota alterations are shared in relapsing and progressive MS, we identified unique bacteria associated with progressive MS and clinical measures of disease. Furthermore, elevated Akkermansia in MS may be a compensatory beneficial response in the MS microbiome. ANN NEUROL 2021;89:1195–1211

METHODSBrain MRI fluid-attenuated inversion-recovery (FLAIR) sequences were performed in 32 multiple sclerosis (MS) patients. Expanded Disability Status Scale (EDSS) score (mean ± standard deviation) was 2 ± 2.0 (range 0-8), disease duration 9.3 ± 8.0 (range .8-29) years. RESULTS FLAIR lesion volume (FLLV