Non-invasive diagnostic criteria of hepatocellular carcinoma: Comparison of diagnostic accuracy of updated LI-RADS with clinical practice guidelines of OPTN-UNOS, AASLD, NCCN, EASL-EORTC, and KLSCG-NCC

Purpose To retrospectively compare the diagnostic performance of different noninvasive diagnostic criteria of HCC including LI-RADS, OPTN-UNOS, AASLD, NCCN, EASL-EORTC, KLCSG-NCC. Materials and methods We reviewed the medical records of 3,491 pathologically examined liver lesions from January-2011 to January-2015 in our institution. 195 lesions in 133 patients (M:F = 100:33) with chronic hepatitis B/C and/or cirrhosis for any etiology were finally included in our study, with 98 lesions >= 2 cm, 72 lesions between 1-2 cm, and 25 lesions < 1 cm. The main comparison was made with the largest nodules of each patient (n = 133). The lesions were retrospectively evaluated for the diagnosis of HCC on DCE-CT or MR using different noninvasive diagnostic criteria including LI-RADS, OPTN-UNOS, AASLD, NCCN, EASL-EORTC, and KLCSG-NCC. With pathological evaluation serving as a gold-standard, sensitivity, specificity, PPV and NPV as well as accuracy of the diagnostic criteria were calculated. Results There was no statistically significant differences in diagnostic accuracy among noninvasive diagnostic criteria. For 133 lesions of the largest lesion per patient, the overall accuracy was highest with LI-RADS criteria (89.3%) and the overall sensitivity was highest with LI-RADS, AASLD, NCCN criteria (all 89.5%). For 1-2 cm lesions, sensitivity decreased for all criteria in the following order: EASL-EORTC (59.1%), KLCSG-NCC (58.3%), LI-RADS, AASLD, NCCN (all 56.5%), and OPTN-UNOS (22.7%) criteria. OPTN-UNOS had the highest specificity in cirrhotic livers, 91.7%. Conclusions The current noninvasive diagnostic criteria of HCC have no statistically significant difference in diagnostic accuracy. Overall, LI-RADS had the highest sensitivity and accuracy among the guidelines. OPTN had the highest specificity for cirrhotic livers.