Purpose: To develop and evaluate an enhanced CT-based radiomics nomogram for predicting preoperative metastasis in epithelial ovarian cancer (EOC). Materials and Methods: 109 patients with histopathology-confirmed EOC were retrospectively enrolled. The volume of interest (VOI) was delineated in preoperative enhanced CT images, and 851 radiomics features were extracted. The radiomics features were filtered by the least absolute shrinkage and selection operator (LASSO), and the radiomics score was calculated using the formula of the radiomics label. A clinical radiomics model and nomogram were constructed by multivariate logistic regression. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) was used to evaluate the prediction effect. Results: 75 patients (68.8%) were histologically confirmed to have metastasis. Eleven nonzero LASSO coefficient radiomics features were selected to develop radiomic model, and four clinical charac-teristics were selected to develop clinical model. The clinical radiomics model for prediction metastasis of EOC achieved areas under the curve (AUCs) of 0.929 (95% CI, 0.8593-0.9996) in the training cohort and 0.909 (95% CI, 0.7921-1.0000) in the test cohort. To facilitate clinical use, a radiomic nomogram was builtedby combined the clinical charac-teristics with Rad-score. The DCAs confirmed that the nomogram could predict metastasis. Conclusions: The radiomics nomogram had significantly superior prediction ability than the clinical model and the radiomics model, which could be suggested as a useful and convenient tool to help clinicians formulate personalized treatment plans for EOC patients.