Computed tomography texture analysis combined with preoperative clinical factors serve as a predictor of early efficacy of transcatheter arterial chemoembolization in hepatocellular carcinoma.

Abstract

To investigate a pre-therapeutic radiomics nomogram to accurately predict hepatocellular carcinoma (HCC) lesion responses to transcatheter arterial chemoembolization (TACE). This retrospective study from January 2012 to 2022 included 92 TACE-treated patients who underwent liver contrast-enhanced CT scan 7days before treatment, having complete clinical information. We extracted quantitative texture parameters and clinical factors for the largest tumors on the baseline arterial and portal venous phase CT images. An adaptive least absolute shrinkage and selection operator (LASSO)-penalized logistic regression identified independent predictors of tumor activity after TACE. We fitted an adaptive LASSO regression model to narrow down the texture features and clinical risk factors of the tumor activity status. The selected texture features were used to construct radiomic scores (RadScore), which demonstrated superior performance in predicting tumor activity on both the training (area under the curve (AUC): 0.881, 95% CI: 0.799-0.963) and testing sets (AUC: 0.88, 95% CI: 0.726-1). A logistic regression-based nomogram was developed using RadScore and four selected clinical features. In the testing set, nomogram total points were significant predictors (P = 0.034), and the training set showed no departure from perfect fit (P = 0.833). Internal validation of the nomogram was obtained for the training (AUC: 0.91, 95% CI: 0.837-0.984) and testing (AUC: 0.889, 95% CI: 0.746-1) sets. We propose a nomogram to predict the early response of HCC lesions to TACE treatment with high accuracy, which may serve as an additional criterion in multidisciplinary decision-making treatment.