Despite the substantial role of chest MRI for the diagnosis and follow-up of thymic cysts, information about inter-reader agreement and optimal MR sequences is still limited. We aimed to investigate the inter-reader agreement for diagnosing thymic cysts using various combinations of MR sequences and to assess the effect of the addition of CT on inter-reader agreement. A total of 76 anterior mediastinal lesions (≤ 30mm) from two tertiary referral hospitals (55 from Institution A and 21 from Institution B) who underwent chest CT and contrast-enhanced chest MR were included. Internal and external reading sets consisted of different combinations of MR sequences (pre- and post-contrast T1-weighted, T2-weighted, subtracted images, and diffusion-weighted imaging [DWI]/apparent diffusion coefficient [ADC] map) and CT. Four and three radiologists independently reviewed internal and external reading sets. The overall inter-reader agreement was moderate (κ = 0.50-0.57) for diagnosing cysts without significant differences between MR sequence combinations (all p-values > 0.05). The mean pairwise inter-reader agreement was the highest (κ = 0.65) when both the subtracted image and DWI/ADC map were provided. The addition of CT had no positive effect on the inter-reader agreement in the internal reading set (κ, from 0.57 to 0.50) but increased inter-reader agreement in the external reading set from moderate (κ = 0.48) to substantial (κ = 0.74). In conclusion, the overall inter-reader agreement for diagnosing thymic cysts on MRI was moderate. MR sequences including both the subtracted image and DWI/ADC map may be optimal in terms of inter-reader agreement.
Read full abstract