Computed tomography-based delta-radiomics analysis for discriminating radiation pneumonitis in patients with esophageal cancer after radiation therapy.

Abstract

PURPOSE\nTo construct a computed tomography (CT)-based delta-radiomics nomogram and corresponding risk classification system for individualized and accurate estimation of severe acute radiation pneumonitis (SARP) in patients with esophageal cancer (EC) after radiation therapy (RT).\n\n\nMETHODS AND MATERIALS\n400 EC patients were enrolled from two independent institutions, and were divided into the training (n\u202f=\u202f200) and validation cohorts (n\u202f=\u202f200). 850 radiomics features of lung were extracted from treatment planning images, including the positioning CT before RT (CT1) and the resetting CT after receiving 40-45Gy (CT2). The longitudinal net changes in radiomics features from CT1 to CT2 were calculated and defined as delta-radiomics features. Least absolute shrinkage and selection operator algorithm was performed to features selection and delta-radiomics signature building. Integrating the signature with multidimensional clinicopathological, dosimetric and hematological predictors of SARP, a novel CT-based delta-radiomics nomogram was established according to multivariate analysis. The clinical application values of nomogram were both evaluated in the training and validation cohorts by concordance index (C-index), calibration curves and decision curve analysis (DCA). Recursive partitioning analysis was utilized to generate a risk classification system.\n\n\nRESULTS\nThe delta-radiomics signature consisting of 24 features was significantly associated with SARP status (P < 0.001). Incorporating it with other high-risk factors that were Subjective Global Assessment score, pulmonary fibrosis score, mean lung dose, and systemic immune inflammation index, the developed delta-radiomics nomogram showed increased improvement in SARP discrimination accuracy with C-index of 0.975 and 0.921 in the training and validation cohorts, respectively. Calibration curves and DCA confirmed the satisfactory clinical feasibility and utility of nomogram. The risk classification system displayed excellent performance on identifying SARP occurrence (P < 0.001).\n\n\nCONCLUSIONS\nThe delta-radiomics nomogram and risk classification system as low-cost and non-invasive means exhibited superior predictive accuracy and provided individualized probability of SARP stratification for EC patients.