biostudies-literatureUnknown12Wu CMedical Science and Technology Project of Zhejiang Province<h4>Objectives</h4>To develop and validate an intuitive computed tomography (CT)-based radiomics nomogram for the prediction and risk stratification of early recurrence (ER) in hepatocellular carcinoma (HCC) patients after partial hepatectomy.<h4>Methods</h4>A total of 132 HCC patients treated with partial hepatectomy were retrospectively enrolled and assigned to training and test sets. Least absolute shrinkage and selection operator and gradient boosting decision tree were used to extract quantitative radiomics features from preoperative contrast-enhanced CT images of the HCC patients. The radiomics features with predictive value for ER were used, either alone or in combination with other predictive features, to construct predictive models. The best performing model was then selected to dFrontiers in oncology896002https://www.ebi.ac.uk/biostudies/studies/S-EPMC9302642biostudies-literatureCT-Based Radiomics Nomogram Improves Risk Stratification and Prediction of Early Recurrence in Hepatocellular Carcinoma After Partial Hepatectomy.PMC9302642Liu YYu SZhang YZhu LWu CChen SfalseCT-Based Radiomics Nomogram Improves Risk Stratification and Prediction of Early Recurrence in Hepatocellular Carcinoma After Partial Hepatectomy.<h4>Objectives</h4>To develop and validate an intuitive computed tomography (CT)-based radiomics nomogram for the prediction and risk stratification of early recurrence (ER) in hepatocellular carcinoma (HCC) patients after partial hepatectomy.<h4>Methods</h4>A total of 132 HCC patients treated with partial hepatectomy were retrospectively enrolled and assigned to training and test sets. Least absolute shrinkage and selection operator and gradient boosting decision tree were used to extract quantitative radiomics features from preoperative contrast-enhanced CT images of the HCC patients. The radiomics features with predictive value for ER were used, either alone or in combination with other predictive features, to construct predictive models. The best performing model was then selected to d2022-01-01T00:00:00Z20222025-04-04T10:47:59.544Z2025-04-04T10:47:59.544ZS-EPMC93026423587514010.3389/fonc.2022.896002