Predicting early recurrence (ER) after radical therapy for HCC patients is critical for the decision of subsequent follow-up and treatment. Radiomic features derived from the medical imaging show great potential to predict prognosis. Here we aim to develop and validate a radiomics nomogram that could predict ER after curative ablation. Total 184 HCC patients treated from August 2007 to August 2014 were included in the study and were divided into the training (n = 129) and validation(n = 55) cohorts randomly. The endpoint was recurrence free survival (RFS). A set of 647 radiomics features were extracted from the 3 phases contrast enhanced computed tomography (CECT) images. The minimum redundancy maximum relevance algorithm (MRMRA) was used for feature selection. The least absolute shrinkage and selection operator (LASSO) Cox regression model was used to build a radiomics signature. Recurrence prediction models were built using clinicopathological factors and radiomics signature, and a prognostic nomogram was developed and validated by calibration. Among the four radiomics models, the portal venous phase model obtained the best performance in the validation subgroup (C-index = 0.736 (95%CI:0.726–0.856)). When adding the clinicopathological factors to the models, the portal venous phase combined model also yielded the best predictive performance for training (C-index = 0.792(95%CI:0.727–0.857) and validation (C-index = 0.755(95%CI:0.651–0.860) subgroup. The combined model indicated a more distinct improvement of predictive power than the simple clinical model (ANOVA, P < 0.0001). This study successfully built a radiomics nomogram that integrated clinicopathological and radiomics features, which can be potentially used to predict ER after curative ablation for HCC patients.

Ten to twenty percent of the hepatocellular carcinoma (HCC) patients fulfilling the Milan criteria (MC) recurred within three years after orthotopic liver transplantation (OLT). We therefore utilize a training cohort to develop an improved prognostic model for predicting the recurrence in these patients. By univariate and multivariate analysis, AFP level [cut-off value: 321 ng/mL, area under the curve (AUC) = 0.724, 95% confidence interval (CI) = 0.604–0.843, P < 0.001] and cytokeratin-19 (CK19) and glypican-3 (GPC3) expression pattern from nine putative prognostic factors were entered in risk factor scoring model to conjecture the tumor recurrence. In the training cohort, the AUC value of the model was 0.767 (95% CI = 0.645–0.890, P < 0.001), which was the highest among all the elements. The model’s performance was then assessed using a validation cohort. In the validation cohort, the AUC value of the model was 0.843 (95% CI = 0.720−0.966, P < 0.001) which was higher than any other elements. The results indicated that model had high performance with good discrimination ability and significantly improved the predictive capacity for the recurrence of HCC patients within MC after OLT.

Hepatocellular carcinomas(HCC) consisted of heterogeneous subtypes with different recurrence probabilities after liver transplantation(LT). Our study aimed to develop an improved model for predicting the recurrence of solitary HCC after LT. In this retrospective study, 151 solitary HCC patients who received orthotopic LT over a period of 10 consecutive years were included. All recipients received graft from deceased donors. The first eligible 50 patients were used as validation cohort and others were utilized to construct the model. A two-tailed P < 0.05 was considered to indicate statistical significance for all analysis. Based on the maximisation of the Youden’s index, the optimal cutoff values for alpha-fetoprotein(AFP) and tumor diameter were 261.6 ng/mL and 3.6 cm, respectively. Vascular involvement includes gross and microscopic vascular invasion. Variables potentially affecting recurrence-free survival(RFS) were examined using univariate and multivariate Cox regression analysis. Univariate and multivariate analysis revealed that AFP, tumor diameter, vascular invasion and cytokeratin-19/glypican-3 sub-typing were independent prognostic factors for RFS, thus comprised the risk scoring model. The AUC values of the model in the cohorts were significantly higher than that of the Milan, UCSF, Fudan and Hangzhou criteria. These findings suggest the model has high performance in predicting early recurrence of solitary HCC patients after LT.

Prediction of early recurrence of hepatocellular carcinoma within the Milan criteria after radical resection Prediction of early recurrence of hepatocellular carcinoma within the Milan criteria after radical resection