A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Medial Meniscal Extrusion in Patients With Medial Meniscus Root Tears: A Systematic Review and Meta-analysis.

Background: Medial meniscal extrusion (MME) has received significant interest because of its correlation with medial meniscus root tears (MMRTs), its potential as a diagnostic tool, and its significance in the progression of knee osteoarthritis (OA). Purpose: To (1) evaluate if MMRTs significantly increase MME compared with nonroot tears (NRTs) and no tears and (2) determine the clinical outcomes of increased MME. Study Design: Systematic review; Level of evidence, 4. Methods: Electronic database searches of PubMed, Embase, Scopus, Web of Science, and Cochrane Central Register of Controlled Trials were conducted on June 6, 2022, in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 checklist criteria. The searches were conducted using the keywords "meniscus tear" and "extrusion." No restrictions were placed on the date of publication. Quality and sensitivity assessments were conducted on included studies. Major MME was defined as an extrusion ≥3 mm. Results: Twenty-two studies involving 7882 knees were included. Compared with patients with NRTs, those with MMRTs had a 1.12-mm greater mean absolute meniscal extrusion (AME) and were 3.45 times more likely to have major MME (P < .001 for both). Compared with patients with no tears, those with MMRTs had a 2.13-mm greater AME (P < .001). Within patients with MMRT, those with widely displaced MMRT had a 1.01-mm greater AME compared with nondisplaced MMRT (P < .001). Patients with OA had a 0.73-mm greater AME and were 3.86 times more likely to have major MME compared with patients without OA (P < .001 for both). Within patients who were not stratified according to MMRT, NRT, or no tears, those who eventually developed OA had a 0.79-mm greater AME than those who did not have OA (P = .02). Conclusion: Patients with MMRTs had higher MME values compared with those with other types of meniscal tears and those without any meniscal tears. Patients with knee OA were more likely to have higher MME compared with those without OA.