TY - JOUR T1 - Fully Automatic Method for Reliable Spinal Cord Compartment Segmentation in Multiple Sclerosis JF - American Journal of Neuroradiology JO - Am. J. Neuroradiol. SP - 218 LP - 227 DO - 10.3174/ajnr.A7756 VL - 44 IS - 2 AU - C. Tsagkas AU - A. Horvath-Huck AU - T. Haas AU - M. Amann AU - A. Todea AU - A. Altermatt AU - J. Müller AU - A. Cagol AU - M. Leimbacher AU - M. Barakovic AU - M. Weigel AU - S. Pezold AU - T. Sprenger AU - L. Kappos AU - O. Bieri AU - C. Granziera AU - P. Cattin AU - K. Parmar Y1 - 2023/02/01 UR - http://www.ajnr.org/content/44/2/218.abstract N2 - BACKGROUND AND PURPOSE: Fully automatic quantification methods of spinal cord compartments are needed to study pathologic changes of the spinal cord GM and WM in MS in vivo. We propose a novel method for automatic spinal cord compartment segmentation (SCORE) in patients with MS.MATERIALS AND METHODS: The cervical spinal cords of 24 patients with MS and 24 sex- and age-matched healthy controls were scanned on a 3T MR imaging system, including an averaged magnetization inversion recovery acquisition sequence. Three experienced raters manually segmented the spinal cord GM and WM, anterior and posterior horns, gray commissure, and MS lesions. Subsequently, manual segmentations were used to train neural segmentation networks of spinal cord compartments with multidimensional gated recurrent units in a 3-fold cross-validation fashion. Total intracranial volumes were quantified using FreeSurfer.RESULTS: The intra- and intersession reproducibility of SCORE was high in all spinal cord compartments (eg, mean relative SD of GM and WM: ≤ 3.50% and ≤1.47%, respectively) and was better than manual segmentations (all P < .001). The accuracy of SCORE compared with manual segmentations was excellent, both in healthy controls and in patients with MS (Dice similarity coefficients of GM and WM: ≥ 0.84 and ≥0.92, respectively). Patients with MS had lower total WM areas (P < .05), and total anterior horn areas (P < .01 respectively), as measured with SCORE.CONCLUSIONS: We demonstrate a novel, reliable quantification method for spinal cord tissue segmentation in healthy controls and patients with MS and other neurologic disorders affecting the spinal cord. Patients with MS have reduced areas in specific spinal cord tissue compartments, which may be used as MS biomarkers.AMIRAaveraged magnetization inversion recovery acquisitionsbSSFPbalanced steady-state free precessionDSCDice similarity coefficientEDSSExpanded Disability Status ScaleHChealthy controlHDHausdorff distanceMDGRUmultidimensional gated recurrent unitsRSDrelative SD (also known as coefficient of variation)SCspinal cordSCWMspinal cord WMSCGMspinal cord GMSCOREautomatic spinal cord compartment segmentationTIVtotal intracranial volume ER -