Assessment of the quality of lung lesions diagnosis in adolescents with osteosarcoma using artificial intelligence (SOPHIA – Smart Osteosarcoma Pediatric Health Imaging Assistant)

Abstract

Background. Lung metastases in osteosarcoma (OS) are the main cause of disease-associated death. The accuracy of the diagnosis of nodules by computed tomography (CT) of the lungs is critically important for determining the disseminated stage of the disease and planning surgical treatment. The study accepted as a working hypothesis the statement that the use of artificial intelligence (AI) in the search for lung nodules can improve the accuracy of diagnosis and reduce the chance of missing metastases. Objective: to evaluate the quality of lung nodules diagnosis in adolescents with OS using AI. Methods. A retrospective comparative assessment of CT scans of adolescents with OS was performed. A pathological nodule with an average size of ≥ 4 mm was considered a target finding. The diagnostic accuracy of the AI algorithm was evaluated, and the number of false positives (FP) and false negatives (FN) was determined. Sensitivity, specificity, accuracy, area under the ROC curve (AUC), positive predictive value, negative predictive value, and F1-measure were calculated. Based on the obtained results, the effectiveness of the algorithm was assessed. Results. 248 CT scans of adolescents with OS were evaluated. The following results were obtained: in 5 cases, the AI algorithm showed a false positive result (2.02%), in 34 cases, it showed a false negative result (13.71%), and in 209 cases, it correctly identified the target pathology (84.27%). The diagnostic accuracy of the algorithm was 0.843 (95% CI 0.794-0.887), and the algorithm's performance was considered satisfactory. By interacting with the AI algorithm in a specific clinical task, the sensitivity could be increased from 0.805 to 0.891, resulting in 8.59% absolute reduction in the number of FN results and in 44% relative reduction. Conclusion. The obtained results objectively confirm the practical value of using the AI algorithm and justify the implementation of AI-assisted systems in the diagnostic protocols for lung metastases in adolescents with OS.