A Radiomics Nomogram for Non-Invasive Prediction of Progression-Free Survival in Esophageal Squamous Cell Carcinoma
Year: 2021
Type: preprint
Study design: Observational Study
Abstract: Objectives: To construct a prognostic model for preoperative prediction based on computed tomography (CT) images of esophageal squamous cell carcinoma (ESCC). Methods: Radiomics signature was constructed using the least absolute shrinkage and selection operator (LASSO) with high throughput radiomics features that extracted from the CT images of 272 patients (204 in training and 68 in validation cohort), who were pathologically confirmed ESCC. Multivariable logistic regression was adopted to build the radiomics signature and another predictive nomogram model, which was composed with radiomics signature, traditional TNM stage and clinical features. Then its performance was assessed by the calibration and decision curve analysis (DCA). Results: 16 radiomics features were selected from 954 to build a radiomics signature，which were significantly associated with progression-free survival (PFS) (p<0.001). The area under the curve (AUC) of performance was 0.891 (95% CI: 0.845-0.936) for training cohort and 0.706 (95% CI: 0.583-0.829) for validation cohort. The radscore of signatures’ combination showed significant discrimination for survival status in both two cohort. Kaplan-Meier survival curve further confirmed the radscore has a better prognostic performance in training cohort. Radiomics nomogram combined radscore with TNM staging showed significant improvement over TNM staging alone in training cohort (C-index, 0.802 vs 0.628; p<0.05), and it is the same with clinical data (C-index, 0.798 vs 0.660; p<0.05). Findings were confirmed in the validation cohort. DCA showed CT-based radiomics model will receive benefit when the threshold probability was between 0 and 0.9. Heat maps revealed associations between radiomics features and tumor stages.Conclusions: Multiparametric CT-based radiomics nomograms provided improved prognostic ability in ESCC.
Source: Research Square
Authors: Ting Yan, lili liu, Meilan Peng, Zhenpeng Yan, Qingyu Wang, Shan Zhang, Lu Wang, Xiaofei Zhuang, Huijuan Liu, Yanchun Ma, Bin Wang, Yongping Cui
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W4246716079