Triphasic CT Radiomics Model for Preoperative Prediction of Hepatocellular Carcinoma Pathological Grading

Abstract

Haibo Huang,1,* Xianpan Pan,2,* Yingdan Zhang,1,* Jie Yang,1 Lei Chen,2 Qinping Zhao,1 Lifeng Huang,1 Wei Lu,3 Yaohong Deng,2 Yingying Huang,4,* Ke Ding1,* 1Department of Radiology, The Third Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530031 People’s Republic of China; 2Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 200232, People’s Republic of China; 3Department of Pathology, The Third Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, 530031, People’s Republic of China; 4Department of Radiology, The First People’s Hospital of Qinzhou, Qinzhou, Guangxi, 530550, People’s Republic of China*These authors contributed equally to this workCorrespondence: Ke Ding, Department of Radiology, The Third Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530031, People’s Republic of China, Email [email protected] Yingying Huang, Department of Radiology, The First People’s Hospital of Qinzhou, Qinzhou, Guangxi, 530031, People’s Republic of China, Email [email protected]: This study aimed to develop and validate a triphasic CT-based radiomics model for the synchronous prediction of multiple critical pathological markers in hepatocellular carcinoma (HCC).Materials and Methods: This retrospective study analyzed 174 patients with 187 hepatocellular carcinoma (HCC) lesions. Radiomic features (n = 2264) were extracted from arterial phase (AP), venous phase (VP), and delayed phase (DP) CT images. Key features were selected using minimum redundancy maximum relevance (mRMR), SelectKBest, and least absolute shrinkage and selection operator (LASSO) algorithms. Logistic regression and support vector machine (SVM) classifiers were employed to develop individual phase-specific models and a triphasic fusion model. Model performance was evaluated through the area under the curve (AUC), sensitivity, specificity, decision curve analysis, and other metrics.Results: The triphasic fusion model demonstrated superior performance. In the testing 1 dataset, the triphasic fusion model achieved AUCs of 0.890 (95% CI: 0.741– 1), 0.895 (95% CI: 0.781– 1) and 0.829 (95% CI: 0.675– 0.984) for Edmondson-Steiner (Ed) grading, Microvascular invasion (MVI) grading, and Satellite nodule (SN) grading, respectively. In the testing 2 (validation) dataset, the triphasic fusion model achieved AUCs of 0.836 (95% CI: 0.739– 0.934), 0.871 (95% CI: 0.748– 0.993) and 0.810 (95% CI: 0.656– 0.963) for Ed, MVI, and SN grading, respectively. The performance of the fusion model was better than that of the single-phase models.Conclusion: The triphasic CT radiomics model provides a noninvasive tool for preoperative prediction of HCC pathological grading (Ed, MVI, SN), enhancing diagnostic accuracy for clinical decision-making and prognostic evaluation.Plain Language Summary: Why is this study important?Preoperative prediction of HCC pathological features (Ed, MVI, and SN grading) is clinically significant.A triphasic CT-based fusion model demonstrated strong predictive performance:Testing 1 dataset: AUCs of 0.890 (Ed), 0.895 (MVI), and 0.829 (SN) grading.Testing 2 (validation) dataset: AUCs of 0.836 (Ed), 0.871 (MVI), and 0.810 (SN) grading.The model aids in preoperative clinical decision-making and prognostic evaluation for HCC patients.Keywords: pathological grading, hepatocellular carcinoma, contrast-enhanced CT, radiomics

Keywords

• Pathological grading
• Hepatocellular carcinoma
• Contrast-enhanced CT
• Radiomics.