Contrast enhanced ultrasound predict hepatocellular carcinoma recurrence: a retrospective observation cohort study

Background: Surgery is the main treatment for hepatocellular carcinoma (HCC), but early recurrence (ER) affects patients' prognosis. Non-invasive screening of high-risk recurrence groups is important for precise treatment to formulate personalized treatment. contrast-enhanced ultrasound (CEUS) may realize this scenario Objectives: Construction and validation of a non-invasive prediction model for ER of HCC after surgery based on CEUS and serological biomarkers. Methods: : 466 patients who underwent CEUS and curative resection between 2016.1.1 and 2019.1.1 were retrospectively recruited from one institution. The training and testing cohorts comprised 326 and 140 patients. We collected CEUS Liver Imaging Reporting and Data System (LI-RADS) grading and serological indicators. Finding risk factors for recurrence of HCC after surgery using univariate and multvariatel analysis, and the Contrast-enhanced Ultrasound Serological (CEUSS) model was constructed. Different models were compared using time-dependent area under the receiver operating characteristic curve (td-AUC) and prediction error. The CEUSS model’s performances in ER prediction were assessed. Results: : Base-line data of the training and testing cohorts were equal. LI-RADS category, α-fetoprotein level, tumor maximum diameter, total bilirubin level, starting time, iso-time, and enhancement pattern were independent hazards, and their hazards ratios were 1.417, 1.309, 1.133, 1.036, 0.883, 0.985, and 0.70, respectively. The AUCs of CEUSS, BCLC, TNM, and CNLC were 0.706, 0.641, 0.647, and 0.636, respectively, in the training cohort and 0.680, 0.583, 0.607, and 0.597, respectively, in the testing cohort. The prediction errors of CEUSS, BCLC, TNM, and CNLC were 0.202, 0.205, 0.205, and 0.200, respectively, in the training cohort and 0.204, 0.221, 0.219, and 0.211, respectively, in the testing cohort. Conclusions: : CEUSS model can effectively screen out high-risk recurrence population, providing an important basis for precise treatment.