Radiomics signature: A potential biomarker for β-arrestin1 phosphorylation prediction in hepatocellular carcinoma

Abstract

Background: The phosphorylation status of β-arrestin1 influences its function as a signal strongly related to sorafenib resistance. This retrospective study aimed to develop and validate radiomics-based models for predicting β-arrestin1 phosphorylation in hepatocellular carcinoma (HCC) using whole-lesion radiomics and visual imaging features on preoperative contrast-enhanced computed tomography (CT) images.

Aim: To develop and validate radiomics-based models for predicting β-arrestin1 phosphorylation in HCC using radiomics with contrast-enhanced CT.

Methods: Ninety-nine HCC patients (training cohort: n = 69; validation cohort: n = 30) receiving systemic sorafenib treatment after surgery were enrolled in this retrospective study. Three-dimensional whole-lesion regions of interest were manually delineated along the tumor margins on portal venous CT images. Radiomics features were generated and selected to build a radiomics score using logistic regression analysis. Imaging features were evaluated by two radiologists independently. All these features were combined to establish clinico-radiological (CR) and clinico-radiological-radiomics (CRR) models by using multivariable logistic regression analysis. The diagnostic performance and clinical usefulness of the models were measured by receiver operating characteristic and decision curves, and the area under the curve (AUC) was determined. Their association with prognosis was evaluated using the Kaplan-Meier method.

Results: Four radiomics features were selected to construct the radiomics score. In the multivariate analysis, alanine aminotransferase level, tumor size and tumor margin on portal venous phase images were found to be significant independent factors for predicting β-arrestin1 phosphorylation-positive HCC and were included in the CR model. The CRR model integrating the radiomics score with clinico-radiological risk factors showed better discriminative performance (AUC = 0.898, 95%CI, 0.820 to 0.977) than the CR model (AUC = 0.794, 95%CI, 0.686 to 0.901; P = 0.011), with increased clinical usefulness confirmed in both the training and validation cohorts using decision curve analysis. The risk of β-arrestin1 phosphorylation predicted by the CRR model was significantly associated with overall survival in the training and validation cohorts (log-rank test, P < 0.05).

Conclusion: The radiomics signature is a reliable tool for evaluating β-arrestin1 phosphorylation which has prognostic significance for HCC patients, providing the potential to better identify patients who would benefit from sorafenib treatment.

Keywords: Computed tomography; Hepatocellular carcinoma; Overall survival; Radiomics; Sorafenib resistance; β-Arrestin1 phosphorylation.

Figure 1

Patient recruitment process.

Figure 2

Performance of the three models. A: The developed clinico-radiological (CR) nomogram; B: The developed clinico-radiological-radiomics (CRR) nomogram. Predictor points are found on the uppermost point scale that corresponds to each variable. On the bottom scale, the points for all variables are added and translated into a β-arrestin1 phosphorylation positivity probability. C: Comparison of receiver operating characteristic (ROC) curves of the radiomics model, CR model and CRR model in the training cohort; D: Comparison of receiver operating characteristic (ROC) curves of the radiomics model, CR model and CRR model in the validation cohort. E: Calibration curves of the three models in the training cohort; F: Calibration curves of the three models in the validation cohort. The actual high expression of p-β-arrestin1 is represented on the y-axis, and the predicted probability is represented on the x-axis. The closer fit of the solid line to the ideal black dotted line indicates a better calibration.

Figure 3

Representative images of contrast-enhanced computed tomography and β-Arrestin1 phosphorylation (magnification, × 100). A: CT images of a 45-year-old man with a 6.3-cm hepatocellular carcinoma (HCC) in the right liver lobe in the plain phase; B: The tumor shows heterogeneous hyperenhancement in the arterial phase; C: The tumor shows washout at the portal venous phase with intratumor necrosis, an ill-defined capsule and a non-smooth tumor margin. D: Immunohistochemical staining shows a β-arrestin1 phosphorylation-negative status at 100× magnification.

Figure 4

Decision curve analysis for each model. A: Decision curve analysis in the training cohort; B: Decision curve analysis in the validation cohort. The y-axis measures the net benefit, and the x-axis is the threshold probability. The gray line represents the hypothesis that all patients are β-arrestin1 phosphorylation-positive. The black line represents the hypothesis that all patients are β-arrestin1 phosphorylation-negative. Among the three models, the clinico-radiological-radiomics (CRR) model provided the highest net benefit compared with the radiomics and clinico-radiological (CR) models.

Figure 5

Overall survival (OS) curve analysis. A: The OS curve estimates by clinic-radiological-radiomics model in patients with β-Arrestin1 phosphorylation positive and β-Arrestin1 phosphorylation negative in the training cohort; B: The OS curve estimates by clinic-radiological-radiomics model in patients with β-Arrestin1 phosphorylation positive and β-Arrestin1 phosphorylation negative in the validation cohort.