Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation

Simple Summary: Personalized therapy of non-small cell lung cancer (NSCLC) relies heavily on histopathological analyses that require invasive biopsies that have relatively high costs, provide limited assessment of tumor heterogeneity and are associated with potentially life-threatening complications. This retrospective study is aimed at evaluating the potential benefit of using predictive models that integrate radiomic features extracted from computed tomography (CT) images and commonly assessed clinical predictors to characterize the overall survival (OS) of stage III NSCLC adenocarcinoma patients receiving chemoradiation. Different than previous studies, our proposed approach explicitly accounts for CT parameter heterogeneity, such as presence or lack of intravenous contrast material and differences in CT scanner vendors through feature harmonization. Using a relatively homogeneous population of 110 patients, our results demonstrate that radiomic biomarkers derived using feature harmonization significantly improved the prediction of OS in our cohort when combined with Eastern Cooperative Oncology Group (ECOG) status and age at diagnosis, suggesting their potential in assisting clinical decision making.) upon the baseline model (C-(score) = 0.65, CI = (0.57, 0.73)). Our results suggest that harmonized radiomic phenotypes can significantly improve OS prediction in stage III NSCLC after chemoradiation.We evaluate radiomic phenotypes derived from CT scans as early predictors of overall survival (OS) after chemoradiation in stage III primary lung adenocarcinoma. We retrospectively analyzed 110 thoracic CT scans acquired between April 2012-October 2018. Patients received a median radiation dose of 66.6 Gy at 1.8 Gy/fraction delivered with proton (55.5%) and photon (44.5%) beam treatment, as well as concurrent chemotherapy (89%) with carboplatin-based (55.5%) and cisplatin-based (36.4%) doublets. A total of 56 death events were recorded. Using manual tumor segmentations, 107 radiomic features were extracted. Feature harmonization using ComBat was performed to mitigate image heterogeneity due to the presence or lack of intravenous contrast material and variability in CT scanner vendors. A binary radiomic phenotype to predict OS was derived through the unsupervised hierarchical clustering of the first principal components explaining 85% of the variance of the radiomic features. C-scores and likelihood ratio tests (LRT) were used to compare the performance of a baseline Cox model based on ECOG status and age, with a model integrating the radiomic phenotype with such clinical predictors. The model integrating the radiomic phenotype (C-score = 0.69, 95% CI = (0.62, 0.77)) significantly improved (p < 0.005) upon the baseline model (C-score = 0.65, CI = (0.57, 0.73)). Our results suggest that harmonized radiomic phenotypes can significantly improve OS prediction in stage III NSCLC after chemoradiation.

Automated summary

Personalized therapy for NSCLC relies on invasive biopsies. This study explores the potential of using predictive models that integrate radiomic features extracted from CT images and clinical predictors to predict the survival of NSCLC patients. The results suggest that radiomic biomarkers derived through feature harmonization significantly improve the prediction of overall survival.