Prediction of Microvascular Invasion in Hepatocellular Carcinoma With Radiomics Fusion Models on Dynamic Contrast-Enhanced Computed Tomography

Abstract

Backbround: Microvascular invasion (MVI) of hepatocellular carcinoma (HCC) is an independent predictor of recurrence and poor outcome following surgical hepatic resection. Prediction of MVI pre-operatively would contribute to the selection of therapy strategies. Therefore, we aimed to investigate MVI of HCC through noninvasive fusion-based radiomics modeling on dynamic contrast enhanced (DCE) computed tomography (CT). Methods: This retrospective study included 111 patients with pathologically proven hepatocellular carcinoma, which comprised 57 MVI-positive and 54 MVI-negative patients. Target volume of interest (VOI) was delineated on four DCE CT phases. The volume of tumor core (Vtc) and seven peripheral tumor regions (Vpt, with varying distances of 2, 4, 6, 8, 10, 12, and 14mm to tumor margin) were obtained. Radiomics features extracted from different combinations of phase(s) and VOI(s) were cross-validated by 150 classification models. The best phase and VOI (or combinations) were determined. The top predictive models were ranked and screened by cross-validation on the training/validation set. The model fusion, a procedure analogous to multidisciplinary consultation, was performed on the top-3 models to generate a final model, which was validated on an independent testing set. Findings: Image features extracted from Vtc + Vpt(12mm) in the portal venous phase (PVP) showed dominant predictive performances over features from other VOIs/phases combinations. Model fusion outperformed a single model in MVI prediction. The weighted fusion method achieved the best predictive performance with an AUC of 0·81, accuracy of 78·3%, sensitivity of 81·8%, and specificity of 75% on the independent testing set. Interpretation: Image features extracted from the PVP with Vtc + Vpt(12mm) are the most reliable features indicative of MVI. Fusion-based radiomics modeling is a promising tool to generate accurate and reproducible results in MVI status prediction in HCC. Funding Statement:: This work was supported by the National Natural Science Foundation of China (81971574, 81874216, 81571665); the National Key Research and Development Program of China (2017YFC0112900); the Natural Science Foundation of Guangdong Province, P.R. China (2018A030313282); the Guangzhou Science and Technology Project, P.R. China (202002030268, 201904010422), and Medical Science and Technology Research Project of Guangdong Province (A2019465). Declaration of Interests: There are no conflicts of interest between any of authors. Ethics Approval Statement: This study was approved by the Institutional Review Board of Guangzhou First People’s Hospital and the requirement for informed consent was waived based on the nature of a retrospective study.