DataSheet_1.docx

Abstract

Objectives: To investigate the prognostic role of radiomic features based on pre-treatment MRI in predicting progression-free survival (PFS) of locally advanced cervical cancer (LACC). Patients and Methods: All 181 women with histologically confirmed LACC, randomly divided into the training cohort (n = 126) and the validation cohort (n = 55). For each patient, we extracted radiomic features from whole tumors on sagittal T2WI and axial DWI. The least absolute shrinkage and selection operator (LASSO) algorithm combined with the Cox survival analysis were applied to select features and construct a radiomic score (Rad-score) model. The cutoff value of the Rad-score was used to divide the patients into high-and low-risk groups by the X-tile. A Kaplan–Meier analysis and the log-rank test were used to assess risk ability of groups in predicting PFS. Afterward, we developed three models, the clinical model, Rad-score, and the combined nomogram. Results: In the training and validation cohorts, the Kaplan-Meier analysis showed high-risk group had a shorter PFS than the low-risk group (p<0.0001 and p<0.0001, respectively), otherwise, the combined nomogram, integrating the Rad-score and patient’s age, hemoglobin, white blood cell, lymph vascular space invasion, demonstrated prominent discrimination, yielded an AUC of 0.879 (95%CI, 0.811-0.947) and 0.820 (95%CI, 0.668-0.971). Delong test verified that the combined nomogram showed better performance in estimating PFS than the clinical model and Rad-score in training cohort (p = 0.038, p = 0.043). Conclusion: The radiomics nomogram performed well in individualized PFS estimation for the patients with LACC, which might guide individual treatment decisions.