RESUMO
OBJECTIVE: To develop and validate a radiomics-clinical nomogram for the detection of the acquired T790M mutation in patients with advanced non-small cell lung cancer (NSCLC) with resistance after the duration of first-line epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitor (TKI) treatment. MATERIALS AND METHODS: Thoracic CT was collected from 120 advanced NSCLC patients who suffered progression on first- or second-generation TKIs. Radiomics signatures were retrieved from the entire tumor. Pearson correlation and the least absolute shrinkage and selection operator (LASSO) regression method were adopted to choose the most suitable radiomics features. Clinical and radiological factors were assessed using univariate and multivariate analysis. Three Machine Learning (ML) models were constructed according to three classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), and RandomForest (RF), combining clinical and radiomic features. A nomogram combining clinical features and the rad score signature was built. The predictive ability of the nomogram was assessed by the ROC curve, calibration curve, and decision curve analysis (DCA). RESULTS: Multivariate regression analysis showed that two clinicopathological characteristics and two radiological features were highly correlated with the acquired T790M mutation, including the progression-free survival (PFS) of first-line EGFR TKIs (P = 0.029), the initial EGFR profile (P = 0.01), vascular convergence (P = 0.043), and air bronchogram (P = 0.030). The AUCs of clinical, radiomics, and combined models using RF classifiers for T790M mutation detection were 0.951 (95% confidence interval [CI] 0.911,0.991), 0.917 (95%CI 0.856,0.978), and 0.961 (95%CI 0.927,0.995) in the training cohort, respectively, higher than those of other classifier models.The calibration curve and Hosmer-Lemeshow Test showed good calibration power, and the DCA demonstrated a significant net benefit. CONCLUSION: A radiomics-clinical nomogram based on CT radiomics proved valuable in non-invasively and efficiently predicting the acquired T790M mutation in patients who suffered progression on first-line TKIs.
RESUMO
Background: The identification of different subtypes of early-stage lung invasive adenocarcinoma before surgery contributes to the precision treatment. Radiomics could be one of the effective and noninvasive identification methods. The value of peritumoral radiomics in predicting the subtypes of early-stage lung invasive adenocarcinoma perhaps clinically useful. Methods: This retrospective study included 937 lung adenocarcinomas which were randomly divided into the training set (n=655) and testing set (n=282) with a ratio of 7:3. This study used the univariate and multivariate analysis to choose independent clinical predictors. Radiomics features were extracted from 18 regions of interest (1 intratumoral region and 17 peritumoral regions). Independent and conjoint prediction models were constructed based on radiomics and clinical features. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, accuracy (ACC), sensitivity (SEN), and specificity (SPE). Significant differences between areas under the ROC (AUCs) were estimated using in the Delong test. Results: Patient age, smoking history, carcinoembryonic antigen (CEA), lesion location, length, width and clinic behavior were the independent predictors of differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes. The highest AUC value among the 19 independent models was obtained for the PTV0~+3 radiomics model with 0.849 for the training set and 0.854 for the testing set. As the peritumoral distance increased, the predictive power of the models decreased. The radiomics-clinical conjoint model was statistically significantly different from the other models in the Delong test (P<0.05). Conclusions: The intratumoral and peritumoral regions contained a wealth of clinical information. The diagnostic efficacy of intra-peritumoral radiomics combined clinical model was further improved, which was particularly important for preoperative staging and treatment decision-making.
