LI-RADS Treatment Response Algorithm: Performance and Diagnostic Accuracy with Radiologic-Pathologic Explant Correlation in patients with SBRT treated hepatocellular carcinoma.

Abstract Purpose: To evaluate the accuracy of LR TRA for assessing viability of HCC treated with SBRT, using explant pathology as the gold standard. Materials and Methods: This retrospective study included patients who underwent SBRT for locoregional treatment of HCC between 2008 and 2019 with subsequent liver transplantation. Five radiologists independently assessed all treated lesions by using the LR-TRA. Imaging and post-transplant histopathology were compared. Lesions were categorized as either completely (100%) or incompletely ( Results: A total of 40 treated lesions in 26 patients (median age 63 years (IQR 59.4-65.5); 23 men) were included. For lesions treated with SBRT, sensitivity for incomplete tumor necrosis across readers ranged between 71-86%, specificity between 85-96% and PPV between 86-92%, when LR-TR Equivocal category were treated as nonviable, accounting for subject clustering. When LR- TR Equivocal category was treated as viable, sensitivity of complete tumor necrosis for lesions treated with SBRT ranged between 88-96%, specificity between 71-93 and NPV between 85-96%. Inter-reader reliability was fair (k =0.22; CI 0.13-0.33). Although a loss of arterial phase hyperenhancement (APHE) was highly correlated with pathologically nonviable tumor on explant, almost ½ of the patients with APHE had pathologically nonviable tumor on explant. Conclusion: LR-TRA v2018 performs well for predicting complete and incomplete necrosis in HCC treated with SBRT. In contrast to other locoregional therapies, the presence of APHE after SBRT does not always indicate viable tumor and suggests that observation may be an appropriate strategy for these patients.