Radiomics models based on multisequence MRI for prediction of PD-1/PD-L1 expression in hepatocellular carcinoma

Abstract The purpose of this study was to explore the efficacy of radiomics based on multisequence MRI to predict the expression of PD-1/PD-L1 in HCC.One hundred eight patients with HCC who underwent contrast-enhanced MRI 2 weeks before surgical resection were enrolled in this retrospective study.Corresponding paraffin sections were collected for immunohistochemistry to detect the expression of PD-1 and PD-L1. All patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3.The radiomics features were extracted from axial fat suppression T2-weighted imaging (FS-T2WI), the arterial phase (A) and portal phase (P) of axial dynamic contrast-enhanced MRI, and the corresponding feature sets were generated. The least absolute shrinkage and selection operator (LASSO) was performed to select the optimal radiomics features for analysis. A logistic regression analysis was performed to construct single-sequence (FS-T2WI, A and P) and multisequence radiomics (M) models. The predictive performance was judged by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts.In the whole cohort, PD-1 expression was positive in 43 patients and PD-L1 expression was positive in 34 patients. The AUC values of the FS-T2WI, A, P and M models to predict the expression of PD-1 were 0.696, 0.843, 0.863, and 0.946 in the training group and 0.669, 0.792, 0.800 and 0.815 in the validation group, respectively.The AUC values of the FS-T2WI, A, P and M models to predict PD-L1 expression were 0.731, 0.800, 0.800, and 0.831 in the training group and 0.621, 0.743, 0.771,and 0.810 in the validation group, respectively. The combined model (M model) performed better than the other radiomics models. The results of this study suggest that a radiomics model based on multisequence MRI had the potential to predict the preoperative expression of PD-1 and PD-L1 in HCC, which may become a imaging biomarker for ICI treatment.