Assessment of LI-RADS Efficacy in the Classification of Hepatocellular Carcinoma and Benign Liver Nodules Using DCE-MRI Features and ADC MRI

Abstract

The Liver Imaging Reporting and Data System (LI-RADS) is a widely utilized tool for classifying liver lesions, particularly in patients at risk for hepatocellular carcinoma (HCC). This study aims to assess the efficacy of LI-RADS in distinguishing between HCC and benign liver nodules by leveraging dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and apparent diffusion coefficient (ADC) values derived from MRI. Between October 2023 and March 2024, 43 patients with suspected HCC underwent MRI evaluation, including DCE-MRI and DWI sequences. The diagnostic performance of various MRI sequences was analyzed, focusing on their ability to differentiate HCC from benign lesions. The diagnostic efficacy of DCE-MRI and ADC in differentiation was evaluated using statistical analyses, such as t-tests and receiver operating characteristic (ROC) curve analysis. SPSS VER 16 was used to analyze the collected data. The study findings reveal that the DCE-MRI arterial phase demonstrated perfect diagnostic accuracy with an area under the curve (AUC) of 1.00, achieving 100% sensitivity and specificity. T2-weighted imaging also exhibited diagnostic solid performance, with an AUC of 0.801, while ADC values from DWI sequences showed limited efficacy in differentiating HCC from benign lesions (AUC=0.512). These findings indicate that DCE-MRI significantly enhances the accuracy of LI-RADS in classifying HCC versus benign liver nodules. This study highlights the importance of incorporating advanced imaging features into LI-RADS to improve the diagnostic precision of liver lesion evaluation in clinical practice.