Accurate prediction of epidermal growth factor receptor mutation status in early‐stage lung adenocarcinoma, using radiomics and clinical features

Abstract

Objectives To develop a nomogram based on CT radiomics and clinical features to predict the epidermal growth factor receptor (EGFR) mutations in early‐stage lung adenocarcinomas. Methods A retrospective analysis of postoperative patients with pathologically confirmed lung adenocarcinoma, which had been tested for EGFR mutations was performed from January 2015 to December 2015. Patients were randomly assigned to training and validation cohorts. A total of 1,078 radiomics features were extracted. least absolute shrinkage and selection operator (LASSO) regression analysis was applied to select clinical and radiomics features, and to establish predictive models. The radiomics score (rad‐score) of each patient was calculated. The discrimination of the model was evaluated with area under the curve. Results 1092 patients (444 men and 648 women; mean age: 59.59±9.6) were enrolled. The radiomics signature consisted of 28 radiomics features and emphysema. The mean validation cohort result of the rad‐score for patients with EGFR mutations (0.814±0.988) was significantly higher than those with EGFR wild‐type (0.315±1.237; p = 0.001). When combined with clinical features, LASSO regression analysis revealed four radiomics features, emphysema, and three clinical features including sex, age, and histologic subtype as associated with to EGFR mutation status. The nomogram that combined radiomics and clinical features significantly improved the predictive discrimination (AUC: 0.723), which is better than that of the radiomics signature alone (AUC: 0.646). Conclusion A relationship between selected radiomics features and EGFR mutant lung adenocarcinomas is demonstrated. A nomogram, combining radiomics features and clinical features for EGFR prediction in early‐stage lung adenocarcinomas, has shown a moderate discriminatory efficiency and high sensitivity, providing additional information for clinicians.

Prediction of oncogene mutation status in non-small cell lung cancer: A systematic review and meta-analysis with a special focus on artificial-intelligence-based methods

“…A hierarchical sROC curve was plotted for the included 24 studies 17, 25, 27, 32, 36, 39, 46, 49-51, 54, 55, 57-60, 62, 64-66, 68-71 that evaluate the performance of AI algorithms in predicting EGFR mutation status in NSCLC ( Supplementary Figure S1 ). Eight studies assessed more than one model 32, 36, 39, 50, 59, 60, 65, 70 . As observed, radiomics-based models exhibited high diagnostic performance in predicting EGFR mutation status with an overall AUC of 0.766.…”

“…The effect of adding clinical variables to radiomics models or to models including both radiomics and deep features 65 (models including clinical data and radiomic or deep features referred in this work as combined models) in the prediction of EGFR mutation was also analyzed. This meta-analysis included 23 studies 25, 26, 28, 32, 33, 38, 39, 46, 51-53, 56-58, 61-69 , of which four of them developed more than one model 32, 39, 56, 67 . Results are depicted in Figure 3 and sROC curve in Supplementary Figure S1 .…”

“…A total of 38 studies met the inclusion criteria for the quantitative assessment ( n = 17,066 patients). Three main different meta-analyses including radiomics-based models were conducted: 1) a meta-analysis including studies focused on the detection of EGFR ( n = 34 studies) 17, 25-28, 32, 33, 36, 38, 39, 46, 49-71 ; 2) a meta-analysis including studies focused on the detection of ALK ( n = 3 studies) 72-74 ; 3) a meta-analysis including studies focused on the detection of KRAS ( n = 4 studies) 47, 50, 54, 62 . In three studies, authors developed models for the detection of both EGFR and KRAS 50, 54, 62 .…”

“…Note that this meta-analysis also included a study 50 in which predictions were based on features extracted by a multi-channel and multi-task deep learning model with the ability to simultaneously detect EGFR and KRAS oncogene mutations; and consequently, did not include radiomics features (only single-task results for the independent prediction of EGFR and KRAS were considered for the quantitative analysis). A hierarchical sROC curve was plotted for the included 24 studies 17, 25, 27, 32, 36, 39, 46, 49-51, 54, 55, 57-60, 62, 64-66, 68-71 that evaluate the performance of AI algorithms in predicting EGFR mutation status in NSCLC ( Supplementary Figure S1 ). Eight studies assessed more than one model 32, 36, 39, 50, 59, 60, 65, 70 .…”

Radiomic Signatures for Predicting EGFR Mutation Status in Lung Cancer Brain Metastases

“…Studies have evaluated the relationship of radiomics features with the isocitrate dehydrogenase gene status of gliomas (12) or the BRAF gene status of melanoma BMs (13). Although several studies have applied radiomics to identify EGFR mutations in either BMs or primary lung cancers using brain MRI, the study populations were relatively small, especially for patients with EGFR mutations, or the EGFR mutation status of the BMs was determined based on the primary tumor status, rather than samples obtained from the BMs (14)(15)(16)(17)(18)(19)(20)(21)(22)(23).…”