An MRI-based radiomics signature and clinical characteristics for survival prediction in early-stage cervical cancer
Ru-ru Zheng, Meng‐Ting Cai, Lan Li, Xiao Wan Huang, Yun Yang, Martin C. Powell, Feng Lin
Abstract
OBJECTIVES: To investigate the prognostic role of magnetic resonance imaging (MRI)-based radiomics signature and clinical characteristics for overall survival (OS) and disease-free survival (DFS) in the early-stage cervical cancer. METHODS: = 63) were enrolled. 792 radiomics features were extracted from T2W and diffusion-weighted imaging (DWI). 19 clinicopathological parameters were collected from the electronic medical record system. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to select significant features to construct prognostic model for OS and DFS. Kaplan-Meier (KM) analysis and log-rank test were applied to identify the association between the radiomics score (Rad-score) and survival time. Nomogram discrimination and calibration were evaluated as well. Associations between radiomics features and clinical parameters were investigated by heatmaps. RESULTS: < 0.05) in the training and validation set. The joint models outperformed both radiomics model and clinicopathological model alone for 3-year OS and DFS estimation. The calibration curves reached an agreement. Heatmap analysis demonstrated significant associations between radiomics features and clinical characteristics. CONCLUSIONS: The MRI-based radiomics nomogram showed a good performance on survival prediction for the OS and DFS in the early-stage cervical cancer. The prediction of the prognostic models could be improved by combining with clinical characteristics, suggesting its potential for clinical application. ADVANCES IN KNOWLEDGE: This is the first study to build the radiomics-derived models based on T2W and DWI images for the prediction of survival outcomes on the early-stage cervical cancer patients, and further construct a combined risk scoring system incorporating the clinical features.