MRI radiomics and nutritional-inflammatory biomarkers: a powerful combination for predicting progression-free survival in cervical cancer patients undergoing concurrent chemoradiotherapy

作者：Qi Yan, Menghan Wu, Jing Zhang, Jiayang Yang, Guannan Lv, Baojun Qu, Yanping Zhang, Yan Xia, Jianbo Song · 发表于：Cancer Imaging · 年份：2024 · DOI：10.1186/s40644-024-00789-2 · 被引用次数：11 · 研究领域：Endometrial and Cervical Cancer Treatments、Inflammatory Biomarkers in Disease Prognosis、Radiomics and Machine Learning in Medical Imaging

OBJECTIVE: This study aims to develop and validate a predictive model that integrates clinical features, MRI radiomics, and nutritional-inflammatory biomarkers to forecast progression-free survival (PFS) in cervical cancer (CC) patients undergoing concurrent chemoradiotherapy (CCRT). The goal is to identify high-risk patients and guide personalized treatment. METHODS: We performed a retrospective analysis of 188 patients from two centers, divided into training (132) and validation (56) sets. Clinical data, systemic inflammatory markers, and immune-nutritional indices were collected. Radiomic features from three MRI sequences were extracted and selected for predictive value. We developed and evaluated five models incorporating clinical features, nutritional-inflammatory indicators, and radiomics using C-index. The best-performing model was used to create a nomogram, which was validated through ROC curves, calibration plots, and decision curve analysis (DCA). RESULTS: Model 5, which integrates clinical features, Systemic Immune-Inflammation Index (SII), Prognostic Nutritional Index (PNI), and MRI radiomics, showed the highest performance. It achieved a C-index of 0.833 (95% CI: 0.792-0.874) in the training set and 0.789 (95% CI: 0.679-0.899) in the validation set. The nomogram derived from Model 5 effectively stratified patients into risk groups, with AUCs of 0.833, 0.941, and 0.973 for 1-year, 3-year, and 5-year PFS in the training set, and 0.812, 0.940, and 0.944 in the valid...