Role of intratumoral and peritumoral CT radiomics for the prediction of EGFR gene mutation in primary lung cancer

Abstract

Objectives To determine the added value of combining intratumoral and peritumoral CT radiomics for the prediction of epidermal growth factor receptor (EGFR) gene mutations in primary lung cancer (PLC). Methods This study included 478 patients with PLC (348 adenocarcinomas and 130 other histological types) who underwent surgical resection and EGFR gene testing. Two radiologists performed segmentation of tumors and peritumoral regions using precontrast high-resolution CT images, and 398 radiomic features (212 intra- and 186 peritumoral features) were extracted. The peritumoral region was defined as the lung parenchyma within a distance of 3 mm from the tumor border. Model performance was estimated using Random Forest, a machine-learning algorithm. Results EGFR mutations were found in 162 tumors; 161 adenocarcinomas, and one pleomorphic carcinoma. After exclusion of poorly reproducible and redundant features, 32 radiomic features remained (14 intra- and 18 peritumoral features) and were included in the model building. For predicting EGFR mutations, combining intra- and peritumoral radiomics significantly improved the performance compared to intratumoral radiomics alone (AUC [area under the receiver operating characteristic curve], 0.774 vs 0.730; p < 0.001). Even in adenocarcinomas only, adding peritumoral radiomics significantly increased performance (AUC, 0.687 vs 0.630; p < 0.001). The predictive performance using radiomics and clinical features was significantly higher than that of clinical features alone (AUC, 0.826 vs 0.777; p = 0.005). Conclusions Combining intra- and peritumoral radiomics improves the predictive accuracy of EGFR mutations and could be used to aid in decision-making of whether to perform biopsy for gene tests. Advances in knowledge Adding peritumoral to intratumoral radiomics yields greater accuracy than intratumoral radiomics alone in predicting EGFR mutations and may serve as a non-invasive method of predicting of the gene status in PLC.

FDG PET texture indices as imaging biomarkers for epidermal growth factor receptor mutation status in lung adenocarcinoma

“…In our study, the accuracy of FDG PET texture indices ranged from 0.621 to 0.712. Yamazaki et al evaluated 14 intratumoral and 18 peritumoral CT radiomics for the prediction of EGFR mutation in lung cancer 18 . The AUCs of intratumoral CT radiomics and combined intratumoral and peritumoral CT radiomics were 0.730 and 0.774, respectively 18 .…”

“…Yamazaki et al evaluated 14 intratumoral and 18 peritumoral CT radiomics for the prediction of EGFR mutation in lung cancer 18 . The AUCs of intratumoral CT radiomics and combined intratumoral and peritumoral CT radiomics were 0.730 and 0.774, respectively 18 . In our study, the AUCs of FDG PET texture indices ranged from 0.662 to 0.753.…”

Investigation of the combination of intratumoral and peritumoral radiomic signatures for predicting epidermal growth factor receptor mutation in lung adenocarcinoma

“…Yamazaki et al reported the usefulness of 3 mm-peritumoral radiomic features for predicting EGFR mutation status. 10 Furthermore, Morales et al reported that peritumoral lung parenchyma within 3 mm excluding the thoracic wall or mediastinum was correlated with overall survival in lung cancer. 29 Therefore, the use of IPRS3 is reasonable and meaningful for predicting the EGFR mutation status.…”

“…Yamazaki et al and Choe et al reported the usefulness of peritumoral radiomic features in predicting EGFR mutation status. 1,10 Their methods used a single setting with peritumoral sizes of 3 and 5 mm from the tumor border. Because the studies used different peritumoral size, optimal peritumoral size for predicting EGFR mutation status must be investigated.…”

“…However, these processes are time consuming, expensive, and invasive. Some researchers have proposed predictive models for EGFR mutations using radiomic features derived from computed tomography images 1,8–10 . Radiomics can analyze tumor phenotypes by automatically extracting numerous quantitative features from medical images, such as CT and/or magnetic resonance images 11 .…”