Diagnostic Performance of LI-RADS Treatment Response Algorithm for Hepatocellular Carcinoma: Adding Ancillary Features to MRI Compared with Enhancement Patterns at CT and MRI

Background: The Liver Imaging Reporting and Data System Treatment Response (LR-TR) algorithm is used to assess the response of hepatocellular carcinoma (HCC) to local-regional therapy (LRT) based on enhancement patterns. The potential value of adding MRI ancillary features (AFs) needs to be investigated. Purpose: To evaluate the potential application of MRI AFs in category adjustment to detect pathologic tumor viability in comparison with the LR-TR algorithm in CT and gadoxetic acid-enhanced MRI. Materials and Methods: This retrospective study included patients with HCCs treated with LRT followed by surgical resection or liver transplantation between January 2014 and December 2017 who underwent both post-LRT CT and gadoxetic acid-enhanced MRI. For each treated observation, treatment response (TR) categories were assigned based on a consensus reading of three radiologists according to the LR-TR algorithm in CT and MRI and according to the MRI-modified TR algorithm in which MRI AFs were allowed for category adjustment. The diagnostic performances of CT LR-TR viable, MRI LR-TR viable, and MRI-modified TR viable categories were compared intraindividually with the McNemar test, with pathologic tumor viability used as a reference standard. Results: A total of 138 patients (119 men; mean age, 58 years +/- 6 9 [standard deviation]) with 138 treated observations (108 pathologically viable) were evaluated. The sensitivity and specificity of CT LR-TR viable and MRI LR-TR viable categories for predicting tumor viability were 73% (79 of 108 lesions; 95% confidence interval [CI]: 64%, 81%) versus 76% (82 of 108 lesions; 95%CI: 67%, 84%) and 90% (27 of 30 lesions; 95% CI: 74%, 98%) versus 83% (25 of 30 lesions; 95% CI: 65%, 94%), respectively,without differences between CT and MRI (P = .65 and P = .63, respectively). MRI-modified TR viable category had higher sensitivity (84% [91 of 108 lesions; 95% CI: 76%, 91%]) than CT or MRI LR-TR viable category (P =.002 and P =.01, respectively),without difference in specificity (80% [24 of 30 lesions]; 95% CI: 61%, 92%) (P =.38 and P..99, respectively). Conclusion: The application of MRI ancillary features to the Liver Imaging Reporting and Data System Treatment Response algorithm resulted in higher sensitivity and no change in specificity compared with CT or MRI enhancement patterns alone in the prediction of pathologic tumor viability in patients with hepatocellular carcinoma. (C) RSNA, 2020