Mullerian duct anomalies: Comparison of MRI diagnosis and clinical diagnosis

OBJECTIVE. The objective of our study was to assess agreement between MRI and clinical diagnosis of mullerian duct anomalies and identify causes of discrepancy. MATERIALS AND METHODS. Images of 103 patients who underwent MRI for suspected mullerian duct anomaly were reviewed. Imaging included axial T1-weighted spin-echo (SE) (TR/TE, 500/10) and sagittal, long-uterine-axis, and short-uterine-axis T2-weighted fast SE (5,000/ 80) sequences. Agreement between original MRI diagnosis and final clinical diagnosis was assessed using the kappa statistic. Two radiologists retrospectively reviewed all cases with inconsistent MRI and clinical diagnoses to identify causes of discrepancy. RESULTS. There was excellent agreement (kappa=0.8) between MRI and clinical diagnoses of mullerian duct anomalies. For evaluation of the uterus, there was agreement in 83 of 103 patients, disagreement in 15 of 103, and agreement could not be determined in five of 103 because of uncertain MRI diagnoses. The main causes of disagreement were MRI diagnosis of septate uteri with two cervices clinically diagnosed as didelphic, partial septate uteri clinically diagnosed as arcuate, and complex anomalies with features of more than one class. The main difficulties for MRI were the detection of small uteri or remnants, characterization of cervical dysgenesis and rare anomalies, overestimation of cervical mucosal folds, characterization of anomalies in the presence of fibroids, and delineation of vaginal abnormalities. CONCLUSION. Despite excellent agreement between MRI and clinical diagnoses of mullerian duct anomalies, there are discrepancies and pitfalls resulting mostly from the absence of a precise and integrated classification scheme, unfamiliarity with rare and complex entities, and suboptimal depiction of some structures on MRI.