Simultaneous Identification of EGFR,KRAS,ERBB2, and TP53 Mutations in Patients with Non-Small Cell Lung Cancer by Machine Learning-Derived Three-Dimensional Radiomics

Multiple genetic mutations are associated with the outcomes of patients with non-small cell lung cancer (NSCLC) after using tyrosine kinase inhibitor, but the cost for detecting multiple genetic mutations is high. Few studies have investigated whether multiple genetic mutations can be simultaneously detected based on image features in patients with NSCLC. We developed a machine learning-derived radiomics approach that can simultaneously discriminate the presence of EGFR, KRAS, ERBB2, and TP53 mutations on CT images in patients with NSCLC. These findings suggest that machine learning-derived radiomics may become a noninvasive and low-cost method to screen for multiple genetic mutations in patients with NSCLC before using next-generation sequencing tests, which can help to improve individualized targeted therapies. READ ARTICLE

Cancers DOI:10.3390/cancers13081814

Authors: Tiening Zhang, Zhihan Xu, Guixue Liu, Beibei Jiang, Geertruida H. de Bock, Harry J. M. Groen, Rozemarijn Vliegenthart, Xueqian Xie

Pre-ClinicalKirk SmithApril 1, 2021NSCLC, Radiomics

Radiomic prediction of mutation status based on MR imaging of lung cancer brain metastases

Lung cancer metastases comprise most of all brain metastases in adults and most brain metastases 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 classify mutational status of the metastatic disease. 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. Brain MR Images were used for segmentation of enhancing tumors and peritumoral edema, and for radiomic feature extraction. The most relevant radiomic features were identified and used with clinical data to train random forest classifiers to classify the mutation status. 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 transloca..... READ ARTICLE

Magnetic Resonance Imaging DOI:10.1016/j.mri.2020.03.002

Authors: Bihong T. Chen, Taihao Jin, Ningrong Ye, Isa Mambetsariev, Ebenezer Daniel, Tao Wang, Chi Wah Wong, Russell C. Rockne, Rivka Colen, Andrei

Biomarkers in Lung Cancer

Key Points: Biomarkers can be used for risk assessment, detection, diagnosis, and prognosis and to personalize treatment in lung cancer. Clinically useful biomarkers for selection of high-risk patients for lung cancer screening and to differentiate early lung cancer from benign pulmonary nodules are needed. Biomarkers for nodule management and determination of high-risk groups for lung cancer screening are at all phases of development, from discovery to clinical utility studies. Current trends in lung cancer biomarker development include the integration of clinical and radiologic features with molecular biomarkers, the application of artificial intelligence to molecular and imaging biomarker development, the use highly sensitive technologies such as next-generation sequencing for molecular exploration, and a commitment to high-quality clinical validation and utility studies. READ ARTICLE

Clinics in Chest Medicine. DOI: 10.1016/j.ccm.2019.10.004

Authors: Catherine R. Sears, Peter J. Mazzone