<b><i>Background:</i></b> Radiomics has emerged as a new approach that can help identify imaging information associated with tumor pathophysiology. We developed and validated a radiomics nomogram for preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC). <b><i>Methods:</i></b> Two hundred and eight patients with pathologically confirmed HCC (training cohort: <i>n</i> = 146; validation cohort: <i>n</i> = 62) who underwent preoperative gadoxetic acid-enhanced magnetic resonance (MR) imaging were included. Least absolute shrinkage and selection operator logistic regression was applied to select features and construct signatures derived from MR images. Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and radiomics signatures associated with MVI, which were then incorporated into the predictive nomogram. The performance of the radiomics nomogram was evaluated by its calibration, discrimination, and clinical utility. <b><i>Results:</i></b> Higher α-fetoprotein level (<i>p</i> = 0.046), nonsmooth tumor margin (<i>p</i> = 0.003), arterial peritumoral enhancement (<i>p &#x3c;</i> 0.001), and the radiomics signatures of hepatobiliary phase (HBP) T1-weighted images (<i>p &#x3c;</i> 0.001) and HBP T1 maps (<i>p &#x3c;</i> 0.001) were independent risk factors of MVI. The predictive model that incorporated the clinicoradiological factors and the radiomic features derived from HBP images outperformed the combination of clinicoradiological factors in the training cohort (area under the curves [AUCs] 0.943 vs. 0.850; <i>p</i> = 0.002), though the validation did not have a statistical significance (AUCs 0.861 vs. 0.759; <i>p</i> = 0.111). The nomogram based on the model exhibited C-index of 0.936 (95% CI 0.895–0.976) and 0.864 (95% CI 0.761–0.967) in the training and validation cohort, fitting well in calibration curves (<i>p</i> &#x3e; 0.05). Decision curve analysis further confirmed the clinical usefulness of the nomogram. <b><i>Conclusions:</i></b> The nomogram incorporating clinicoradiological risk factors and radiomic features derived from HBP images achieved satisfactory preoperative prediction of the individualized risk of MVI in patients with HCC.

Purpose To evaluate the potential role of diffusion kurtosis imaging and conventional magnetic resonance (MR) imaging findings including standard monoexponential model of diffusion-weighted imaging and morphologic features for preoperative prediction of microvascular invasion (MVI) of hepatocellular carcinoma (HCC). Materials and Methods Institutional review board approval and written informed consent were obtained. Between September 2015 and November 2016, 84 patients (median age, 54 years; range, 29-79 years) with 92 histopathologically confirmed HCCs (40 MVI-positive lesions and 52 MVI-negative lesions) were analyzed. Preoperative MR imaging examinations including diffusion kurtosis imaging (b values: 0, 200, 500, 1000, 1500, and 2000 sec/mm) were performed and kurtosis, diffusivity, and apparent diffusion coefficient maps were calculated. Morphologic features of conventional MR images were also evaluated. Univariate and multivariate logistic regression analyses were used to evaluate the relative value of these parameters as potential predictors of MVI. Results Features significantly related to MVI of HCC at univariate analysis were increased mean kurtosis value (P < .001), decreased mean diffusivity value (P = .033) and apparent diffusion coefficient value (P = .011), and presence of infiltrative border with irregular shape (P = .005) and irregular circumferential enhancement (P = .026). At multivariate analysis, mean kurtosis value (odds ratio, 6.25; P = .001), as well as irregular circumferential enhancement (odds ratio, 6.92; P = .046), were independent risk factors for MVI of HCC. The mean kurtosis value for MVI of HCC showed an area under the receiver operating characteristic curve of 0.784 (optimal cutoff value was 0.917). Conclusion Higher mean kurtosis values in combination with irregular circumferential enhancement are potential predictive biomarkers for MVI of HCC. RSNA, 2017.