A novel fast knee cartilage segmentation technique for T2 measurements at MR imaging--data from the Osteoarthritis Initiative.

Magnetic resonance imaging (MRI) T(2) relaxation time assesses non-invasively cartilage composition and can be used as early biomarker for knee osteoarthritis. Most knee cartilage segmentation techniques were primarily developed for volume measurements in DESS or SPGR sequences. For T(2) quantifications, these segmentations need to be superimposed on T(2) maps. However, given that these procedures are time consuming and require manual alignment, using them for analysis of T(2) maps in large clinical trials like the Osteoarthritis Initiative (OAI) is challenging. A novel direct segmentation technique (DST) for T(2) maps was therefore developed. Using the DST, T(2) measurements were performed and compared with those determined with an established segmentation superimposition technique (SST). MR images of five OAI participants were analysed with both techniques three times by one reader and five different images sets additionally with DST three times by two readers. Segmentations and T(2) measurements of one knee required on average 63±3min with DST (vs 302±13min for volume and T(2) measurements with SST). Bland-Altman plots indicated good agreement between the two segmentation techniques, respectively the two readers. Reproducibility errors of both techniques (DST vs SST) were similar (P>0.05) for whole knee cartilage mean T(2) (1.46% vs 2.18%), laminar (up to 2.53% vs 3.19%) and texture analysis (up to 8.34% vs 9.45%). Inter-reader reproducibility errors of DST were higher for texture analysis (up to 15.59%) than for mean T(2) (1.57%) and laminar analysis (up to 2.17%). Due to these results, the novel DST can be recommended for T(2) measurements in large clinical trials like the OAI.