Perfusion-CT analysis for assessment of hepatocellular carcinoma lesions: diagnostic value of different perfusion maps.

Abstract

Computed tomography liver perfusion (CTLP) has been improved in recent years, offering a variety of perfusion-parametric maps. A map that better discriminates hepatocellular carcinoma (HCC) is still to be found. To compare different CTLP maps, regarding their ability to differentiate cirrhotic or non-cirrhotic parenchyma from malignant HCC. Twenty-six patients (11 cirrhotic) with 50 diagnosed HCC lesions, underwent CTLP on a 128-row dual-energy CT system. Nine different maps were generated. Regions of interest (ROIs) were positioned on non-tumorous parenchyma and on HCCs found on previous magnetic resonance imaging. Perfusion parameters for non-cirrhotic and cirrhotic livers were compared. Receiver operating characteristic (ROC) analysis was employed to evaluate each map's ability to discriminate HCCs from non-tumorous livers. Comparison of ROC curves was performed to evaluate statistical significance of differences in the discriminating efficiency of derived perfusion maps. Perfusion parameters for non-tumorous liver and HCCs recorded in cirrhotic patients did not significantly differ from corresponding values recorded in non-cirrhotic patients ( P > 0.05). The highest power for HCC discrimination was found for the maximum-slope-of-increase (MSI) parametric map, with estimated the area under ROC curve of 0.997. An MSI cut-off criterion of 2.2 HU/s was found to provide 96% sensitivity and 100% specificity. Time to peak, blood flow, and transit time to peak were also found to have high discriminating power. Among available CTLP-derived perfusion parameters, MSI was found to provide the highest diagnostic accuracy in discriminating HCCs from non-tumorous parenchyma. Perfusion parameters for non-tumorous livers and HCCs were not found to significantly differ between cirrhotic and non-cirrhotic patients.