Automatic detection of temporomandibular joint osteoarthritis radiographic features using deep learning artificial intelligence. A Diagnostic accuracy study

• Published in: Journal of stomatology, oral and maxillofacial surgery p. 102124
• Main Authors: Mourad, Louloua, Aboelsaad, Nayer, Talaat, Wael M., Fahmy, Nada M.H., Abdelrahman, Hams H., El-Mahallawy, Yehia
• Format: Journal Article
• Language: English
• Published: Elsevier Masson SAS 31.10.2024
• Subjects: Artificial intelligence; Diagnosis; Osteoarthritis; Temporomandibular joint; Temporomandibular joint; Diagnosis; Osteoarthritis; Artificial intelligence
• ISSN: 2468-7855; 2468-7855
• DOI: 10.1016/j.jormas.2024.102124

•Object identification neural network Artificial Intelligence model could act as an important diagnostic-aid for radiographic confirmation of temporomandibular joint osteoarthritis.•The diagnostic performance of the Artificial Intelligence model in temporomandibular joint osteoarthritis radiographic features identification was favourable.•Artificial Intelligence model is a contemporary diagnostic modality with promising outcomes and the ability for differentiation of radiographic features with acceptable sensitivity and specificity. The purpose of this study was to investigate the diagnostic performance of a neural network Artificial Intelligence model for the radiographic confirmation of Temporomandibular Joint Osteoarthritis in reference to an experienced radiologist. The diagnostic performance of an AI model in identifying radiographic features in patients with TMJ-OA was evaluated in a diagnostic accuracy cohort study. Adult patients elected for radiographic examination by the Diagnostic Criteria for Temporomandibular Disorders decision tree were included. Cone-beam computed Tomography images were evaluated by object detection YOLO deep learning model. The diagnostic performance was verified against examiner radiographic evaluation. The differences between the AI model and examiner were non-significant statistically, except in the subcortical cyst (P=0.049*). AI model showed substantial to near-perfect levels of agreement when compared to those of the examiner data. Regarding each radiographic phenotype, the AI model reported favorable sensitivity, specificity, accuracy, and highly statistically significant Receiver Operating Characteristic (ROC) analysis (p<0.001). Area Under Curve ranged from 0.872, for surface erosion, to 0.911 for subcortical cyst. AI object detection model could open the horizon for a valid, automated, and convenient modality for TMJ-OA radiographic confirmation and radiomic features identification with a significant diagnostic power.