Radiomic analysis based on magnetic resonance imaging for the prediction of VEGF expression in hepatocellular carcinoma patients

Abstract

Objective: The purpose of this study was to investigate the ability of radiomic characteristics of magnetic resonance images to predict vascular endothelial growth factor (VEGF) expression in hepatocellular carcinoma (HCC) patients.

Methods: One hundred and twenty-four patients with HCC who underwent fat-suppressed T2-weighted imaging (FS-T2WI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) one week before surgical resection were enrolled in this retrospective study. Immunohistochemical analysis was used to evaluate the expression level of VEGF. Radiomic features were extracted from the axial FS-T2WI, DCE-MRI (arterial phase and portal venous phase) images of axial MRI. Least absolute shrinkage and selection operator (LASSO) and stepwise regression analyses were performed to select the best radiomic features. Multivariate logistic regression models were constructed and validated using tenfold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models.

Results: Our results show that there were 94 patients with high VEGF expression and 30 patients with low VEGF expression among the 124 HCC patients. The FS-T2WI, DCE-MRI and combined MRI radiomics models had AUCs of 0.8713, 0.7819, and 0.9191, respectively. There was no significant difference in the AUC between the FS-T2WI radiomics model and the DCE-MRI radiomics model (p > 0.05), but the AUC for the combined model was significantly greater than the AUCs for the other two models (p < 0.05) according to the DeLong test. The combined model had the greatest net benefit according to the DCA results.

Conclusion: The radiomic model based on multisequence MR images has the potential to predict VEGF expression in HCC patients. The combined model showed the best performance.

Keywords: Angiogenesis; Hepatocellular carcinoma (HCC); Magnetic resonance imaging (MRI); Radiomics; Targeted therapy; Vascular endothelial growth factor (VEGF).

Fig. 1

Immunohistochemical staining of HCC tissue using a VEGF antibody (A) low VEGF expression (× 200); (B) high VEGF expression (× 200)

Fig. 2

The volume of interest (VOI) was delineated layer by layer on axial FS-T2WI (A), in the arterial phase (B), in the portal venous phase (C), covering the entire tumor and avoiding areas of surrounding bile ducts and blood vessels as much as possible

Fig. 3

Stability assessment of the extracted MRI radiomics features by the ICC (A) FS-T2WI; (B) DCE-MRI arterial phase; (C) DCE-MRI portal venous phase

Fig. 4

Radiomic feature selection using LASSO regression analysis (A1–A2) FS-T2WI; (B1–B2) DCE-MRI (arterial phase and portal venous phase)

Fig. 5

(A) ROC curves for the 10-fold cross-validation of the FS-T2WI model; (B) ROC curves for the 10-fold cross-validation of the DCE-MRI (arterial phase and portal venous phase) model; (C) ROC curves for the 10-fold cross-validation of the combined model

Fig. 6

(A) FFS-T2WI model calibration curve; (B) DCE-MRI model calibration curve; (C) combined model calibration curve; calibration curve—the predicted probability of the model and the actual probability; that is, the closer the nomogram is to the ideal curve, the better the ft of the model

Fig. 7

(A) comparison of the ROC curves for the prediction of VEGF expression by various models; (B) clinical DCA of 3 models; the y-axis represents the standardized net benefit, and the x-axis represents the high risk threshold; dark red (without VEGF expression) and blue (with VEGF expression) represent 2 extreme cases, and it is better if the curve is far from the 2 extreme cases