Objectives: Spinal cord injuries (SCI) require extensive efforts to predict the outcome of patients. While the ASIA Impairment Scale is the gold standard to assess patients with SCI, it has some limitations due to the subjectivity and impracticality in certain cases. Recent advances in machine learning (ML) and image recognition have prompted research into using these tools to predict outcomes. The aim of this study is to present a comprehensive analysis using deep learning techniques to evaluate and predict cervical spine injuries from MRI scans. Materials & Method: This is a cross-sectional database study, with patients admitted with traumatic and nontraumatic cervical SCI from 2019 to 2022 were included in our study. MRI images were labelled by four senior resident physicians. We trained a deep convolutional neural network using axial and sagittal cervical MRI images from our dataset and assessed model performance. Result: In the axial spinal cord segmentation, we achieved a dice score of 0.94 for and IoU score of 0.89. In the sagittal spinal cord segmentation, we obtained a dice scores up to 0.9201 and IoU scores up to 0.8541. The model for axial image score classification gave a satisfactory result with an f1 score of 0.72 and AUC of 0.79. Conclusion: Deep learning has been used in automated diagnostic tools, showing promise for significant future advancement. Our models were effectively able to identify cervical spinal cord injury on T2-weighted MR images with satisfactory performance. Further research is necessary to create an even more advanced model for predicting patient outcomes in spinal cord injury cases.

Aims: Lumbar post-surgery syndrome (LPSS) can cause persistent low back pain after lumbar surgery, and epidural fibrosis is a recognised contributor to ongoing radicular symptoms and functional limitation. This case report describes short-term pain and functional outcomes after fluoroscopy-guided percutaneous epidural adhesiolysis (Racz procedure) in six patients with refractory LPSS. Presentation of Case: Six patients with chronic low back pain after previous lumbar decompression, stabilisation, or fusion procedures were treated at our institution. Eligibility required symptoms for at least six months, inadequate response to at least three months of conservative management, and magnetic resonance imaging evidence of epidural fibrosis or adhesions. The cohort comprised three men and three women, with a mean age of 59.3 years (range, 52-67 years). Outcomes were assessed before the procedure and at three months using the Visual Analogue Scale (VAS), Roland Morris Disability Questionnaire (RDQ), and Oswestry Disability Index (ODI). Mean VAS decreased from 8.0 to 3.0, mean RDQ from 18.2 to 7.5, and mean ODI from 66.0% to 25.3%. No complication was documented. Discussion: Improvement may have reflected mechanical disruption of adhesions, improved epidural medication spread, dilution of inflammatory mediators, enzymatic degradation of scar-related matrix, and targeted delivery of local anaesthetic and corticosteroid to symptomatic nerve roots. Conclusion: Epidural adhesiolysis was associated with short-term reductions in pain and disability in selected patients with LPSS who had not responded adequately to conservative treatment. Longer follow-up and controlled evaluation are required to define durability and patient selection more clearly.