Development and Validation of an MRI-based Radiomics Nomogram for Assessing Deep Myometrial Invasion in Early Stage Endometrial Adenocarcinoma.

Abstract

To establish a radiomics nomogram for detecting deep myometrial invasion (DMI) in early stage endometrioid adenocarcinoma (EAC). A total of 266 patients with stage I EAC were divided into training (n=185) and test groups (n=81). Logistic regression were used to identify clinical predictors. Radiomics features were extracted and selected from multiparameter MR images. The important clinical factors and radiomics features were integrated into a nomogram. A receiver operating characteristic curve was used to evaluate the nomogram. Two radiologists evaluated MR images with or without the help of the nomogram to detect DMI. The clinical benefit of using the nomogram was evaluated by decision curve analysis (DCA) and by calculating net reclassification index (NRI) and integrated discrimination index (IDI). Age and CA125 were independent clinical predictors. The area under the curves of the clinical parameters, radiomics signature and nomogram in evaluating DMI were 0.744, 0.869 and 0.883, respectively. The accuracies of the two radiologists increased from 79.0% and 80.2% to 90.1% and 92.5% when they used the nomogram. The NRI of the two radiologists were 0.262 and 0.318, and the IDI were 0.322 and 0.405. According to DCA, the nomogram showed a higher net benefit than the radiomics signature or unaided radiologists. Cross-validation showed the outcome of radiomics analysis may not be influenced by changes in field strength. The radiomics nomogram based on radiomics features and clinical factors can help radiologists evaluate DMI and improve their accuracy in predicting DMI in early stage EAC.