Validation of a semiautomated spinal cord segmentation method

• Published in: Journal of magnetic resonance imaging Vol. 41; no. 2; pp. 454 - 459
• Main Authors: El Mendili, Mohamed-Mounir, Chen, Raphaël, Tiret, Brice, Pélégrini-Issac, Mélanie, Cohen-Adad, Julien, Lehéricy, Stéphane, Pradat, Pierre-François, Benali, Habib
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.02.2015; Wiley Subscription Services, Inc
• Subjects: Adult; Amyotrophic Lateral Sclerosis - pathology; atrophy measurement; Case-Control Studies; cross-sectional area; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; MRI; Muscular Atrophy - pathology; Reproducibility of Results; segmentation; Signal-To-Noise Ratio; spinal cord; Spinal Cord Injuries - diagnosis; cross-sectional area; segmentation; spinal cord; MRI; atrophy measurement
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.24571

Purpose To validate semiautomated spinal cord segmentation in healthy subjects and patients with neurodegenerative diseases and trauma. Materials and Methods Forty‐nine healthy subjects, as well as 29 patients with amyotrophic lateral sclerosis, 19 with spinal muscular atrophy, and 14 with spinal cord injuries were studied. Cord area was measured from T2‐weighted 3D turbo spin echo images (cord levels from C2 to T9) using the semiautomated segmentation method of Losseff et al (Brain [1996] 119(Pt 3):701–708), compared with manual segmentation. Reproducibility was evaluated using the inter‐ and intraobserver coefficient of variation (CoV). Accuracy was assessed using the Dice similarity coefficient (DSC). Robustness to initialization was assessed by simulating modifications to the contours drawn manually prior to segmentation. Results Mean interobserver CoV was 4.00% for manual segmentation (1.90% for Losseff's method) in the cervical region and 5.62% (respectively 2.19%) in the thoracic region. Mean intraobserver CoV was 2.34% for manual segmentation (1.08% for Losseff's method) in the cervical region and 2.35% (respectively 1.34%) in the thoracic region. DSC was high (0.96) in both cervical and thoracic regions. DSC remained higher than 0.8 even when modifying initial contours by 50%. Conclusion The semiautomated segmentation method showed high reproducibility and accuracy in measuring spinal cord area. J. Magn. Reson. Imaging 2015;41:454–459.© 2013 Wiley Periodicals, Inc.