Preoperative prediction of recurrence risk factors in operable cervical cancer based on clinical-radiomics features

Xue Du ^1* Chunbao Chen ¹ Min Li ^1,2*

• ¹ North Sichuan Medical College, Nanchong, China
• ² Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan Province, China

Objective: To investigate the value of preoperative prediction of risk factors for recurrence of operable cervical cancer based on the radiomic features of biparametric magnetic resonance imaging (bp-MRI) combined with clinical features. Method: Retrospective collection of cervical cancer cases undergoing radical hysterectomy + pelvic and/or para-aortic lymph node dissection at the Affiliated Hospital of North Sichuan Medical College. Region of interest (ROI) was outlined using 3D slicer software, and radiomics after feature extraction and feature screening using the least absolute shrinkage and selection operator (LASSO) algorithm. Logistic regression algorithms were used to construct a fusion clinical-radiomics model to visualize with Nomogram. Receiver operating characteristic (ROC), DeLong test, calibration curve (CC) and decision curve (DC) were used to evaluate the predictive performance and clinical benefit of the model. Result: A total of 99 patients with cervical cancer were included in this study, with 79 and 20 cases in the train and test groups. Seventeen key features were selected for radiomics model construction. Three clinical features were screened to construct a clinical model. A fusion model of the radiomics model combined with the clinical model was constructed.The area under curve (AUC) in the train group was 0.710 (95%CI 0.602-0.819), 0.892 (95% CI 0.826-0.958), 0.906 (95% CI 0.842-0.970), for the comparative clinical model, radiomics model and fusion model, respectively, and the AUC in the test group were 0.620(95% CI 0.366-0.874), 0.860(95%CI 0.677-1.000), 0.880 (95%CI 0.690-1.000), respectively. The DeLong test showed a statistically significant difference between the AUC values of the fusion model and the clinical model (P < 0.05). DCA showed that the fusion model with the greatest net benefit when the threshold probability was around 0.5.The fusion model constructed based on bp-MRI radiomics features combined with clinical features provides an important reference for predicting the risk status of recurrence in operable cervical cancer. This study is a preliminary exploratory result, and further large-scale, multicenter studies are needed to validate.