Preoperative radiomics model using gadobenate dimeglumine-enhanced magnetic resonance imaging for predicting β-catenin mutation in patients with hepatocellular carcinoma: A retrospective study

Fengxia Zeng; Hui Dai; Xu Li; Le Guo; Ningyang Jia; Jun Yang; Danping Huang; Hui Zeng; Weiguo Chen; Ling Zhang; Genggeng Qin

doi:10.3389/fonc.2022.916126

Preoperative radiomics model using gadobenate dimeglumine-enhanced magnetic resonance imaging for predicting β-catenin mutation in patients with hepatocellular carcinoma: A retrospective study

Front Oncol. 2022 Sep 16:12:916126. doi: 10.3389/fonc.2022.916126. eCollection 2022.

Authors

Fengxia Zeng¹, Hui Dai^{2

3}, Xu Li⁴, Le Guo¹, Ningyang Jia⁵, Jun Yang¹, Danping Huang¹, Hui Zeng¹, Weiguo Chen¹, Ling Zhang¹, Genggeng Qin^{1

6}

Affiliations

¹ Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
² Hospital Office, Ganzhou People's Hospital, Ganzhou, China.
³ Hospital Office, Ganzhou Hospital-Nanfang Hospital, Southern Medical University, Ganzhou, China.
⁴ School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
⁵ Department of Radiology, Eastern Hepatobiliary Surgery Hospital, Second Military Medical University, Shanghai, China.
⁶ Department of Radiology, Ganzhou Hospital-Nanfang Hospital, Southern Medical University, Ganzhou, China.

Abstract

Objective: To compare and evaluate radiomics models to preoperatively predict β-catenin mutation in patients with hepatocellular carcinoma (HCC).

Methods: Ninety-eight patients who underwent preoperative gadobenate dimeglumine (Gd-BOPTA)-enhanced MRI were retrospectively included. Volumes of interest were manually delineated on arterial phase, portal venous phase, delay phase, and hepatobiliary phase (HBP) images. Radiomics features extracted from different combinations of imaging phases were analyzed and validated. A linear support vector classifier was applied to develop different models.

Results: Among all 15 types of radiomics models, the model with the best performance was seen in the R^HBP radiomics model. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity of the R^HBP radiomics model in the training and validation cohorts were 0.86 (95% confidence interval [CI], 0.75-0.93), 0.75, 1.0, and 0.65 and 0.82 (95% CI, 0.63-0.93), 0.73, 0.67, and 0.76, respectively. The combined model integrated radiomics features in the R^HBP radiomics model, and signatures in the clinical model did not improve further compared to the single HBP radiomics model with AUCs of 0.86 and 0.76. Good calibration for the best R^HBP radiomics model was displayed in both cohorts; the decision curve showed that the net benefit could achieve 0.15. The most important radiomics features were low and high gray-level zone emphases based on gray-level size zone matrix with the same Shapley additive explanation values of 0.424.

Conclusion: The R^HBP radiomics model may be used as an effective model indicative of HCCs with β-catenin mutation preoperatively and thus could guide personalized medicine.

Keywords: Gd-BOPTA; hepatocellular carcinoma; magnetic resonance imaging; radiomics; β-catenin mutation.