MATERIALS AND METHODS: Contrast enhanced computed tomography (CT) images of 194 multi-racial NSCLC patients (79 EGFR mutants and 115 wildtypes) were collected from three different countries using 5 manufacturers' scanners with a variety of scanning parameters. Ninety-nine cases obtained from the University of Malaya Medical Centre (UMMC) in Malaysia were used for training and validation procedures. Forty-one cases collected from the Kyushu University Hospital (KUH) in Japan and fifty-four cases obtained from The Cancer Imaging Archive (TCIA) in America were used for a test procedure. Radiomic features were obtained from BN maps, which represent topologically invariant heterogeneous characteristics of lung cancer on CT images, by applying histogram- and texture-based feature computations. A BN-based signature was determined using support vector machine (SVM) models with the best combination of features that maximized a robustness index (RI) which defined a higher total area under receiver operating characteristics curves (AUCs) and lower difference of AUCs between the training and the validation. The SVM model was built using the signature and optimized in a five-fold cross validation. The BN-based model was compared to conventional original image (OI)- and wavelet-decomposition (WD)-based models with respect to the RI between the validation and the test.
RESULTS: The BN-based model showed a higher RI of 1.51 compared with the models based on the OI (RI: 1.33) and the WD (RI: 1.29).
CONCLUSION: The proposed model showed higher robustness than the conventional models in the identification of EGFR mutations among NSCLC patients. The results suggested the robustness of the BN-based approach against variations in image scanner/scanning parameters.
EXPERIMENTAL DESIGN: Tumor tissue EGFRm status was determined at screening using the central cobas tissue test or a local tissue test. Baseline circulating tumor (ct)DNA EGFRm status was retrospectively determined with the central cobas plasma test.
RESULTS: Of 994 patients screened, 556 were randomized (289 and 267 with central and local EGFR test results, respectively) and 438 failed screening. Of those randomized from local EGFR test results, 217 patients had available central test results; 211/217 (97%) were retrospectively confirmed EGFRm positive by central cobas tissue test. Using reference central cobas tissue test results, positive percent agreements with cobas plasma test results for Ex19del and L858R detection were 79% [95% confidence interval (CI), 74-84] and 68% (95% CI, 61-75), respectively. Progression-free survival (PFS) superiority with osimertinib over comparator EGFR-TKI remained consistent irrespective of randomization route (central/local EGFRm-positive tissue test). In both treatment arms, PFS was prolonged in plasma ctDNA EGFRm-negative (23.5 and 15.0 months) versus -positive patients (15.2 and 9.7 months).
CONCLUSIONS: Our results support utility of cobas tissue and plasma testing to aid selection of patients with EGFRm advanced NSCLC for first-line osimertinib treatment. Lack of EGFRm detection in plasma was associated with prolonged PFS versus patients plasma EGFRm positive, potentially due to patients having lower tumor burden.