DCE-MRI-based radiomics in predicting angiopoietin-2 expression in hepatocellular carcinoma

• Published in: Abdominal imaging Vol. 48; no. 11; pp. 3343 - 3352
• Main Authors: Zheng, Jing, Du, Pei-Zhuo, Yang, Cui, Tao, Yun-Yun, Li, Li, Li, Zu-Mao, Yang, Lin
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2023; Springer Nature B.V
• Subjects: Angiopoietin; Cancer; Decision analysis; Gastroenterology; Hepatobiliary; Hepatocellular carcinoma; Hepatology; Imaging; Immunohistochemistry; Liver cancer; Magnetic resonance imaging; Medical imaging; Medicine; Medicine & Public Health; Radiology; Radiomics; Regression analysis; Angiogenesis; Hepatocellular carcinoma; MRI; Radiomics
• ISSN: 2366-0058; 2366-004X; 2366-0058
• DOI: 10.1007/s00261-023-04007-8

Background Hepatocellular carcinoma (HCC) is the sixth most common cancer, and the third leading cause of cancer death worldwide. Studies have shown that increased angiopoietin-2 (Ang-2) expression relative to Ang-1 expression in tumors is associated with a poor prognosis.The purpose of this study was to investigate the efficacy of predicting Ang-2 expression in HCC by preoperative dynamic contrast‐enhanced magnetic resonance imaging (DCE-MRI)-based radiomics. Methods The data of 52 patients with HCC who underwent surgical resection in our hospital were retrospectively analyzed. Ang-2 expression in HCC was analyzed by immunohistochemistry. All patients underwent preoperative upper abdominal DCE-MRI and intravoxel incoherent motion diffusion-weighted imaging scans. Radiomics features were extracted from the early and late arterial and portal phases of axial DCE-MRI. Univariate analysis and least absolute shrinkage and selection operator (LASSO) was performed to select the optimal radiomics features for analysis. A logistic regression analysis was performed to establish a DCE-MRI radiomics model, clinic-radiologic (CR) model and combined model integrating the radiomics score with CR factors. The stability of each model was verified by 10-fold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models. Results Among the 52 HCC patients, high Ang-2 expression was found in 30, and low Ang-2 expression was found in 22. The areas under the ROC curve (AUCs) for the radiomics model, CR model and combined model for predicting Ang-2 expression were 0.800, 0.874, and 0.933, respectively. The DeLong test showed that there was no significant difference in the AUC between the radiomics model and the CR model ( p  > 0.05) but that the AUC for the combined model was significantly greater than those for the other 2 models ( p  < 0.05). The DCA results showed that the combined model outperformed the other 2 models and had the highest net benefit. Conclusion The DCE-MRI-based radiomics model has the potential to predict Ang-2 expression in HCC patients; the combined model integrating the radiomics score with CR factors can further improve the prediction performance. Graphical abstract