Nazarian, Ara

AbstractPurposeWhile several artificial intelligence (AI)‐assisted medical imaging applications are reported in the recent orthopaedic literature, comparison of the clinical efficacy and utility of these applications is currently lacking. The aim of this systematic review is to evaluate the effectiveness and reliability of AI applications in orthopaedic imaging, focusing on their impact on diagnostic accuracy, image segmentation and operational efficiency across various imaging modalities.MethodsBased on the PRISMA guidelines, a comprehensive literature search of PubMed, Cochrane and Scopus databases was performed, using combinations of keywords and MeSH descriptors ('AI', 'ML', 'deep learning', 'orthopaedic surgery' and 'imaging') from inception to March 2024. Included were studies published between September 2018 and February 2024, which evaluated machine learning (ML) model effectiveness in improving orthopaedic imaging. Studies with insufficient data regarding the output variable used to assess the reliability of the ML model, those applying deterministic algorithms, unrelated topics, protocol studies, and other systematic reviews were excluded from the final synthesis. The Joanna Briggs Institute (JBI) Critical Appraisal tool and the Risk Of Bias In Non‐randomised Studies‐of Interventions (ROBINS‐I) tool were applied for the assessment of bias among the included studies.ResultsThe 53 included studies reported the use of 11.990.643 images from several diagnostic instruments. A total of 39 studies reported details in terms of the Dice Similarity Coefficient (DSC), while both accuracy and sensitivity were documented across 15 studies. Precision was reported by 14, specificity by nine, and the F1 score by four of the included studies. Three studies applied the area under the curve (AUC) method to evaluate ML model performance. Among the studies included in the final synthesis, Convolutional Neural Networks (CNN) emerged as the most frequently applied category of ML models, present in 17 studies (32%).ConclusionThe systematic review highlights the diverse application of AI in orthopaedic imaging, demonstrating the capability of various machine learning models in accurately segmenting and analysing orthopaedic images. The results indicate that AI models achieve high performance metrics across different imaging modalities. However, the current body of literature lacks comprehensive statistical analysis and randomized controlled trials, underscoring the need for further research to validate these findings in clinical settings.Level of evidenceSystematic Review; Level of evidence IV.

Abstract Purpose: Pathologic fractures could be prevented if reliable methods of fracture risk assessment were available. A multicenter prospective study was conducted to identify significant predictors of physicians' treatment plan for skeletal metastasis based on clinical fracture risk assessments and the proposed CT-based Rigidity Analysis (CTRA). Experimental Design: Orthopedic oncologists selected a treatment plan for 124 patients with 149 metastatic lesions based on the Mirels method. Then, CTRA was performed, and the results were provided to the physicians, who were asked to reassess their treatment plan. The pre- and post-CTRA treatment plans were compared to identify cases in which the treatment plan was changed based on the CTRA report. Patients were followed for a 4-month period to establish the incidence of pathologic fractures. Results: Pain, lesion type, and lesion size were significant predictors of the pre-CTRA plan. After providing the CTRA results, physicians changed their plan for 36 patients. CTRA results, pain, and primary source of metastasis were significant predictors of the post-CTRA plan. Follow-up of patients who did not undergo fixation resulted in 7 fractures; CTRA predicted these fractures with 100% sensitivity and 90% specificity, whereas the Mirels method was 71% sensitive and 50% specific. Conclusions: Lesion type and size and pain level influenced the physicians' plans for the management of metastatic lesions. Physicians' treatment plans and fracture risk predictions were significantly influenced by the availability of CTRA results. Due to its high sensitivity and specificity, CTRA could potentially be used as a screening method for pathologic fractures. Clin Cancer Res; 21(11); 2514–9. ©2015 AACR.