Preoperative prediction of microvascular invasion in hepatocellular carcinoma: a radiomic nomogram based on MRI

•The radiomic features were significantly associated with MVI. •Radiomic signature was an independent risk factor of MVI. •The radiomic model showed good accuracy for MVI prediction in HCC patients. AIM To develop a reliable model to predict microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) by combining a large number of clinical and imaging examinations, especially the radiomic features of magnetic resonance imaging (MRI). MATERIALS AND METHODS Three hundred and one consecutive patients from two centres were enrolled. Least absolute shrinkage and selection operator (LASSO) regression was used to shrink the feature size, and logistic regression was used to construct a predictive radiomic signature. The ability of the nomogram to discriminate MVI in patients with HCC was evaluated using area under the curve (AUC) of receiver operating characteristics (ROC), accuracy, and calibration curves. RESULTS The radiomic signature showed a significant association with MVI (p<0.001 for all data sets). Other useful predictors of MVI included non-smooth tumour margin, internal arteries, and the alpha-fetoprotein (AFP) level. The nomogram demonstrated a strong prognostic capability in the training set and both validation sets, providing AUCs of 0.914 (95% confidence interval [CI] 0.853–0.956), 0.872 (95% CI: 0.757–0.946), and 0.881 (95% CI: 0.806–0.934), respectively. CONCLUSIONS The preoperative radiomic nomogram, incorporating clinical risk factors and a radiomic signature, could predict MVI in patients with HCC. The MRI-based radiomic–clinical model predicted the MVI of HCC effectively and was more efficient compared with the radiomic model or clinical model alone. To develop a reliable model to predict microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) by combining a large number of clinical and imaging examinations, especially the radiomic features of magnetic resonance imaging (MRI). Three hundred and one consecutive patients from two centres were enrolled. Least absolute shrinkage and selection operator (LASSO) regression was used to shrink the feature size, and logistic regression was used to construct a predictive radiomic signature. The ability of the nomogram to discriminate MVI in patients with HCC was evaluated using area under the curve (AUC) of receiver operating characteristics (ROC), accuracy, and calibration curves. The radiomic signature showed a significant association with MVI (p<0.001 for all data sets). Other useful predictors of MVI included non-smooth tumour margin, internal arteries, and the alpha-fetoprotein (AFP) level. The nomogram demonstrated a strong prognostic capability in the training set and both validation sets, providing AUCs of 0.914 (95% confidence interval [CI] 0.853–0.956), 0.872 (95% CI: 0.757–0.946), and 0.881 (95% CI: 0.806–0.934), respectively. The preoperative radiomic nomogram, incorporating clinical risk factors and a radiomic signature, could predict MVI in patients with HCC. The MRI-based radiomic–clinical model predicted the MVI of HCC effectively and was more efficient compared with the radiomic model or clinical model alone.