Multiparametric mri-based radiomics nomogram for predicting lymph-vascular space invasion in cervical cancer

Abstract Purpose To develop and validate a multiparametric magnetic resonance imaging (mpMRI)-based radiomics model for predicting lymph-vascular space invasion (LVSI) of cervical cancer (CC). Methods The data of 177 CC patients were retrospectively collected and randomly divided into the training cohort ( n =123) and testing cohort ( n = 54). All patients received preoperative MRI. Feature selection and radiomics model construction were performed using max-relevance and min-redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) on the training cohort. The models were established based on the extracted features. The optimal model was selected and combined with clinical independent risk factors to establish the radiomics fusion model and the nomogram. The diagnostic performance of the model was assessed by the area under the curve. Results Feature selection extracted the thirteen most important features for model construction. These radiomics features and one clinical characteristic were selected showed favorable discrimination between LVSI and non-LVSI groups. The AUCs of the radiomics nomogram and the mpMRI radiomics model were 0.838 and 0.835 in the training cohort, and 0.837 and 0.817 in the testing cohort. Conclusion The nomogram model based on mpMRI radiomics has high diagnostic performance for preoperative prediction of LVSI in patients with CC.