Feasibility of T2WI-MRI-based radiomics nomogram for predicting normal-sized pelvic lymph node metastasis in cervical cancer patients.

Abstract

To investigate the feasibility of T2WI-based radiomics nomogram analysis to non-invasively predict normal-sized pelvic lymph node (LN) metastasis (LNM) in cervical cancer patients. Preoperative images of 219 normal-sized pathologically confirmed LNs from 132 cervical cancer patients admitted to our hospital between January 2013 and March 2020 were retrospectively reviewed. Regions of interests (ROIs) were separately delineated on whole LNs and tumors. The maximum-relevance and minimum-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods were used for the construction of radiomics signature. Logistic regression modeling was employed to build models based on clinical features on LN T2WI (model 1), model 1 combined with LN radiomics features (model 2), and model 2 combined with tumor score (model 3). Diagnostic performance was assessed and compared. Both model 2 and model 3 showed higher diagnostic accuracy (training: model 2 0.75, model 3 0.78, model 1 0.72; validation: model 2 0.77, model 3 0.69, model 1 0.66) and AUC (training: model 2 0.77, model 3 0.82, model 1 0.74; validation: model 2 0.75, model 3 0.74, model 1 0.70) than clinical model 1. Diagnostic performance of model 3 was improved compared with model 2 in primary cohort, but reduced in validation cohort. However, the differences did not show obvious statistical difference (p = 0.05 and p = 0.15). T2WI-based radiomics nomogram incorporating the LN radiomics signature with the clinical morphological LN features is promising for predicting the normal-sized pelvic LNM in cervical cancer patients. The original tumor radiomics analysis did not significantly improve the differential diagnosis of LNM. • The combination of LN radiomics signature with LN clinical morphological features on T2WI could discriminate LNM relatively well. • The tumor radiomics analysis did not significantly improve the differential diagnosis of LNM.