Search

Background Return to work (RTW) might be delayed in patients with complicated mild traumatic brain injury (MTBI), i.e., MTBI patients with associated traumatic intracranial lesions. However, the effect of different types of lesions on RTW has not studied before. We investigated whether traumatic intracranial lesions detected by CT and MRI are associated with return to work and post-concussion symptoms in patients with MTBI. Methods We prospectively followed up 113 adult patients with MTBI that underwent a brain MRI within 3–17 days after injury. Return to work was assessed with one-day accuracy up to one year after injury. Rivermead Post-Concussion Symptoms Questionnaire (RPQ) and Glasgow Outcome Scale Extended (GOS-E) were conducted one month after injury. A Kaplan–Meier log-rank analysis was performed to analyze the differences in RTW. Results Full RTW-% one year after injury was 98%. There were 38 patients with complicated MTBI, who had delayed median RTW compared to uncomplicated MTBI group (17 vs. 6 days), and more post-concussion symptoms (median RPQ 12.0 vs. 6.5). Further, RTW was more delayed in patients with multiple types of traumatic intracranial lesions visible in MRI (31 days, n = 19) and when lesions were detected in the primary CT (31 days, n = 24). There were no significant differences in GOS-E. Conclusions The imaging results that were most clearly associated with delayed RTW were positive primary CT and multiple types of lesions in MRI. RTW-% of patients with MTBI was excellent and a single intracranial lesion does not seem to be a predictive factor of disability to work.

Purpose Severity of white matter lesion (WML) is typically evaluated on magnetic resonance images (MRI), yet the more accessible, faster, and less expensive method is computed tomography (CT). Our objective was to study whether WML can be automatically segmented from CT images using a convolutional neural network (CNN). The second aim was to compare CT segmentation with MRI segmentation. Methods The brain images from the Helsinki University Hospital clinical image archive were systematically screened to make CT-MRI image pairs. Selection criteria for the study were that both CT and MRI images were acquired within 6 weeks. In total, 147 image pairs were included. We used CNN to segment WML from CT images. Training and testing of CNN for CT was performed using 10-fold cross-validation, and the segmentation results were compared with the corresponding segmentations from MRI. Results A Pearson correlation of 0.94 was obtained between the automatic WML volumes of MRI and CT segmentations. The average Dice similarity index validating the overlap between CT and FLAIR segmentations was 0.68 for the Fazekas 3 group. Conclusion CNN-based segmentation of CT images may provide a means to evaluate the severity of WML and establish a link between CT WML patterns and the current standard MRI-based visual rating scale.