Radiomic Prediction of Mutation Status Based on MR Imaging of Lung Cancer Brain Metastases

Background: Lung cancer metastases comprise the majority of all brain metastases in adults, most of which are diagnosed by magnetic resonance (MR) scans. The purpose of this study was to conduct an MR imaging-based radiomic analysis of brain metastatic lesions from patients with primary lung cancer to predict mutational status of the metastatic disease. Methods: We retrospectively identified lung cancer patients with brain metastases treated at our institution between 2009 and 2017 who underwent genotype testing of their primary lung cancer. T1-weighted contrast-enhanced and T2-weighted fluid-attenuated inversion recovery brain MR images were used for segmentation of the enhancing tumors and peritumoral edema, respectively, and for radiomic feature extraction. The most relevant radiomic features were identified and used with clinical data including demographic information, additional sites of metastases, and tumor information to train random forest classifiers to predict mutation status. Findings: Of 110 patients in the study cohort (mean age 57·51 ± 12·32 years; M: F=37:73), 75 had an EGFR mutation, 21 had an ALK translocation, and 15 had a KRAS mutation. One patient had both ALK translocation and EGFR mutation. The KRAS mutation-positive group had a significantly higher percentage of smokers than the EGFR mutation-positive (p=0·0002) and ALK translocation-positive (p=0·002) groups. The majority of radiomic features most relevant for mutation prediction were textural. Model building using both radiomic features and clinical data yielded more accurate predictions than using either alone. For classification of EGFR, ALK, and KRAS alteration status, the combined model resulted in area-under-the-curve (AUC) values based on cross-validation of 0·923, 0·916, and 0·960, respectively. Interpretation: Our study demonstrated that MR imaging-based radiomic analysis of brain metastases in patients with primary lung cancer can accurately predict mutation status. This approach may be useful for devising treatment strategies and informing prognosis. Funding: This work was supported by the National Cancer Institute of the National Institutes of Health under Grants No. P30CA033572 and 1U54CA209978-01A1. Declaration of Interest: AH reports personal fees from fMRI Consultants, LLC, outside the submitted work. All other authors declare no competing interests. Ethical Approval: The study was approved by the institutional review board at City of Hope National Medical Center and informed consent was waived due to the retrospective nature of this study. The study was conducted in accordance with the Declaration of Helsinki.