Optimization of Quantitative Dynamic Postgadolinium MRI Technique Using Normalized Ratios for the Evaluation of Temporomandibular Joint Synovitis in Patients with Juvenile Idiopathic Arthritis

BACKGROUND AND PURPOSE: MR imaging has been shown to be useful in the diagnosis of juvenile idiopathic arthritis of the temporomandibular joint. Prior MR imaging approaches have relied mainly on the subjective interpretation of synovial enhancement as a marker for synovial inflammation. Although, more recently, several attempts have been made to quantify synovial enhancement, these methods have not taken into account the dynamic enhancement characteristics of the temporomandibular joint and the effect of sampling time. Our aim was to develop a clinically feasible, reproducible, dynamic, contrast-enhanced MR imaging technique for the quantitative assessment of temporomandibular joint synovitis in patients with juvenile idiopathic arthritis and to study the effect of sampling time on the evaluation of synovitis. MATERIALS AND METHODS: This was a retrospective study of all patients who had dynamic, contrast-enhanced coronal T1 3T MR imaging through the temporomandibular joint at our institution between January 1, 2015, and July 8, 2016. Patients in this cohort included those with a history of juvenile idiopathic arthritis and control patients who underwent MR imaging for other routine, clinical purposes. Synovial enhancement was calculated for each temporomandibular joint using 3 different types of equations termed normalization ratios. The enhancement profiles generated by each equation were studied to determine which provided the best discrimination between affected and unaffected joints, was the least susceptible to sampling errors, and was the most clinically feasible. RESULTS: A ratio of synovial enhancement (defined as the difference between the postgadolinium and the pregadolinium T1 signal of the synovium) to the postgadolinium signal of the longus capitis provided the best discrimination between affected and unaffected joints, the least susceptibility to sampling error, and was thought to be the most clinically feasible method of quantification of synovial inflammation. Additional synovial enhancement ratios studied did not provide the same level rates of discrimination between the affected and unaffected joints and were thought to be too temporally variable to provide reliable clinical use. CONCLUSIONS: We provide a robust, reproducible, dynamic gadolinium-enhanced MR imaging technique for the quantitative assessment of temporomandibular joint synovitis in patients with juvenile idiopathic arthritis.