Objective: To develop and validate a radiomics nomogrambased on gadolinium-ethoxybenzyl-diethylenetriamine (Gd-EOB-DTPA) enhanced magnetic resonance imaging (MRI)for pretreatment prediction of Immunoscore (0–2 vs. 3–4) inhepatocellular carcinoma (HCC) patients. Methods: The study included 207 (training cohort: n = 150;validation cohort: n = 57) HCC patients with hepatectomywho underwent preoperative Gd-EOB-DTPA-enhanced MRI.The volumes of interest enclosing hepatic lesions, includingintratumoral and peritumoral regions, were manuallydelineated in the hepatobiliary phase of MRI images, fromwhich 1,044 quantitative features were extracted and analyzed.The Extremely Randomized Tree method was used toselect radiomics features for building a radiomics model. Aradiomics-based clinical nomogram was developed based onthe selected radiomics features and significant clinical variablesassociated with Immunoscore. Nomogram discrimination andcalibration were also assessed. Results: The combined intratumoral and peritumoralradiomics model showed a better predicting performance inImmunoscore than the intratumoral radiomics model [areaunder the receiver operating characteristic curve (AUC), 0.904(95% CI: 0.855–0.953) vs. 0.823 (95% CI: 0.747–0.899), P =0.036]. The radiomics-based clinical nomogram showed animprovement over the combined radiomics model regardingpredicting Immunoscore in the training cohort [AUC, 0.926(95% CI: 0.884–0.967) vs. 0.904 (95% CI: 0.855–0.953)],although the differences were not statistically significant (P =0.128). Results were confirmed in the validation cohort andcalibration curves showed good agreement. Conclusions: Radiomics-based clinical nomogram incorporatingclinical data and the combined radiomics features from Gd-EOB-DTPA enhanced MRI images is effective in predictingImmunoscore of HCC patients, and may therefore assist cliniciansto asseess potential benefits of prognosis before treatment. DOI: 10.20892/j.issn.2095-3941.2018.S023
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)