Multiple Machine-Learning Fusion Model Based on Gd-EOB-DTPA-Enhanced MRI and Aminotransferase-to-Platelet Ratio and Gamma-Glutamyl Transferase-to-Platelet Ratio to Predict Microvascular Invasion in Solitary Hepatocellular Carcinoma: A Multicenter Study

Abstract

Fei Wang,1,2 Chun Yue Yan,3 Yuan Qin,4 Zheng Ming Wang,1 Dan Liu,1 Ying He,1 Ming Yang,2 Li Wen,1 Dong Zhang1 1Department of Radiology, XinQiao Hospital of Army Medical University, Chongqing, 400037, People’s Republic of China; 2Department of Medical Imaging, Luzhou People’s Hospital, Luzhou, 646000, People’s Republic of China; 3Department of Emergency Medicine, Luzhou People’s Hospital, Luzhou, 646000, People’s Republic of China; 4Department of Radiology, Chongqing University Three Gorges Hospital, Chongqing, 404031, People’s Republic of ChinaCorrespondence: Dong Zhang, Department of Radiology, Xin Qiao Hospital, Army Medical University, Chongqing, 400037, People’s Republic of China, Tel [phone], Email [email protected]: Currently, it is still confused whether preoperative aminotransferase-to-platelet ratio (APRI) and gamma-glutamyl transferase-to-platelet ratio (GPR) can predict microvascular invasion (MVI) in solitary hepatocellular carcinoma (HCC). We aimed to develop and validate a machine-learning integration model for predicting MVI using APRI, GPR and gadoxetic acid disodium (Gd-EOB-DTPA) enhanced MRI.Methods: A total of 314 patients from XinQiao Hospital of Army Medical University were divided chronologically into training set (n = 220) and internal validation set (n = 94), and recurrence-free survival was determined to follow up after surgery. Seventy-three patients from Chongqing University Three Gorges Hospital and Luzhou People’s Hospital served as external validation set. Overall, 387 patients with solitary HCC were analyzed as whole dataset set. Least absolute shrinkage and selection operator, tenfold cross-validation and multivariate logistic regression were used to gradually filter features. Six machine-learning models and an ensemble of the all models (ENS) were built. The area under the receiver operating characteristic curve (AUC) and decision curve analysis were used to evaluate model’s performance.Results: APRI, GPR, HBPratio3 ([liver SI‒tumor SI]/liver SI), PLT, peritumoral enhancement, non-smooth margin and peritumoral hypointensity were independent risk factors for MVI. Six machine-learning models showed good performance for predicting MVI in training set (AUCs range, 0.793– 0.875), internal validation set (0.715– 0.832), external validation set (0.636– 0.746) and whole dataset set (0.756– 0.850). The ENS achieved the highest AUCs (0.879 vs 0.858 vs 0.839 vs 0.851) in four cohorts with excellent calibration and more net benefit. Subgroup analysis indicated that ENS obtained excellent AUCs (0.900 vs 0.809 vs 0.865 vs 0.908) in HCC > 5cm, ≤ 5cm, ≤ 3cm and ≤ 2cm cohorts. Kaplan‒Meier survival curves indicated that ENS achieved excellent stratification for MVI status.Conclusion: The APRI and GPR may be new potential biomarkers for predicting MVI of HCC. The ENS achieved optimal performance for predicting MVI in different sizes HCC and may aid in the individualized selection of surgical procedures.Keywords: hepatocellular carcinoma, microvascular invasion, inflammatory biomarker, magnetic resonance imaging, machine learning

Keywords

• hepatocellular carcinoma
• microvascular invasion
• inflammatory biomarker
• magnetic resonance imaging
• machine learning