RESUMEN
Purpose: To develop a deep learning tool for the automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury (SCI). Material and Methods: This retrospective study included a cohort of SCI patients from three sites enrolled between July 2002 and February 2023. A deep learning model, SCIseg, was trained in a three-phase process involving active learning for the automatic segmentation of intramedullary SCI lesions and the spinal cord. The data consisted of T2-weighted MRI acquired using different scanner manufacturers with heterogeneous image resolutions (isotropic/anisotropic), orientations (axial/sagittal), lesion etiologies (traumatic/ischemic/hemorrhagic) and lesions spread across the cervical, thoracic and lumbar spine. The segmentations from the proposed model were visually and quantitatively compared with other open-source baselines. Wilcoxon signed-rank test was used to compare quantitative MRI biomarkers (lesion volume, lesion length, and maximal axial damage ratio) computed from manual lesion masks and those obtained automatically with SCIseg predictions. Results: MRI data from 191 SCI patients (mean age, 48.1 years ± 17.9 [SD]; 142 males) were used for model training and evaluation. SCIseg achieved the best segmentation performance for both the cord and lesions. There was no statistically significant difference between lesion length and maximal axial damage ratio computed from manually annotated lesions and those obtained using SCIseg. Conclusion: Automatic segmentation of intramedullary lesions commonly seen in SCI replaces the tedious manual annotation process and enables the extraction of relevant lesion morphometrics in large cohorts. The proposed model segments lesions across different etiologies, scanner manufacturers, and heterogeneous image resolutions. SCIseg is open-source and accessible through the Spinal Cord Toolbox.
RESUMEN
BACKGROUND AND PURPOSE: In acute spinal cord injury (SCI), magnetic resonance imaging (MRI) reveals tissue bridges and neurodegeneration for 2 years. This 5-year study aims to track initial lesion changes, subsequent neurodegeneration, and their impact on recovery. METHODS: This prospective longitudinal study enrolled acute SCI patients and healthy controls who were assessed clinically-and by MRI-regularly from 3 days postinjury up to 60 months. We employed histologically cross-validated quantitative MRI sequences sensitive to volume, myelin, and iron changes, thereby reflecting indirectly processes of neurodegeneration and neuroinflammation. General linear models tracked lesion and remote changes in volume, myelin- and iron-sensitive magnetic resonance indices over 5 years. Associations between lesion, degeneration, and recovery (using the Spinal Cord Independence Measure [SCIM] questionnaire and the International Standards for Neurological Classification of Spinal Cord Injury total motor score) were assessed. RESULTS: Patients' motor scores improved by an average of 12.86 (95% confidence interval [CI] = 6.70-19.00) points, and SCIM by 26.08 (95% CI = 17.00-35.20) points. Within 3-28 days post-SCI, lesion size decreased by more than two-thirds (3 days: 302.52 ± 185.80 mm2 , 28 days: 76.77 ± 88.62 mm2 ), revealing tissue bridges. Cervical cord and corticospinal tract volumes transiently increased in SCI patients by 5% and 3%, respectively, accompanied by cervical myelin decreases and iron increases. Over time, progressive atrophy was observed in both regions, which was linked to early lesion dynamics. Tissue bridges, reduced swelling, and myelin content decreases were predictive of long-term motor score recovery and improved SCIM score. CONCLUSIONS: Studying acute changes and their impact on longer follow-up provides insights into SCI trajectory, highlighting the importance of acute intervention while indicating the potential to influence outcomes in the later stages.
