Reliability of cortical lesion detection on double inversion recovery MRI applying the MAGNIMS-Criteria in multiple sclerosis patients within a 16-months period

Purpose In patients with multiple sclerosis (MS), Double Inversion Recovery (DIR) magnetic resonance imaging (MRI) can be used to identify cortical lesions (CL). We sought to evaluate the reliability of CL detection on DIR longitudinally at multiple subsequent time-points applying the MAGNIMs scoring criteria for CLs. Methods 26 MS patients received a 3T-MRI (Siemens, Skyra) with DIR at 12 time-points (TP) within a 16 months period. Scans were assessed in random order by two different raters. Both raters separately marked all CLs on each scan and total lesion numbers were obtained for each scan-TP and patient. After a retrospective re-evaluation, the number of consensus CLs (conL) was defined as the total number of CLs, which both raters finally agreed on. CLs volumes, relative signal intensities and CLs localizations were determined. Both ratings (conL vs. non-consensus scoring) were compared for further analysis. Results A total number of n = 334 CLs were identified by both raters in 26 MS patients with a first agreement of both raters on 160 out of 334 of the CLs found (kappa = 0.48). After the retrospective re-evaluation, consensus agreement increased to 233 out of 334 CL (kappa = 0.69). 93.8% of conL were visible in at least 2 consecutive TP. 74.7% of the conL were visible in all 12 consecutive TP. ConL had greater mean lesion volumes and higher mean signal intensities compared to lesions that were only detected by one of the raters (p<0.05). A higher number of CLs in the frontal, parietal, temporal and occipital lobe were identified by both raters than the number of those only identified by one of the raters (p<0.05). Conclusions After a first assessment, slightly less than a half of the CL were considered as reliably detectable on longitudinal DIR images. A retrospective re-evaluation notably increased the consensus agreement. However, this finding is narrowed, considering the fact that retrospective evaluation steps might not be practicable in clinical routine. Lesions that were not reliably identifiable by both raters seem to be characterized by lower signal intensity and smaller size, or located in distinct anatomical brain regions.