Diagnostic accuracy of synovial chondromatosis of the temporomandibular joint on magnetic resonance imaging

The purpose of this study was to evaluate the diagnostic accuracy of magnetic resonance imaging (MRI) for synovial chondromatosis (SC) of the temporomandibular joint (TMJ). In this study, 1415 patients (2109 joints) with temporomandibular joint disorders were collected between January 2012 and January 2017. All patients had a preoperative MRI examination and were treated by either arthroscopy or open surgery. On reviewing all MRI images, the number of "positive", "suspicious", and "negative" cases was collected afterwards, then the number of reported SC cases in operative data was recorded. The SPSS software was used to process all collected data. The kappa coefficient and ROC curve (AUC-index) with sensitivity and specificity were calculated to evaluate the consistency between MRI and arthroscopy/open surgery. Compared to 156 joints with SC detected by arthroscopy and open surgery, the results of MRI examination showed "positive" in 117 joints, and "negative" in 1938 joints. The number of "true positive", and "true negative" cases was 95, and 1897 respectively. The AUC-index was 0.86 (0.82-0.90) with a kappa coefficient of 0.74 (P < 0.05). In conclusion, the incidence of synovial chondromatosis diagnosed on MRI was in accordance with the arthroscopic and open surgery. Therefore, being a relatively non-invasive tool, MRI could be recommended as an effective diagnostic modality for SC.