Detection of Mutation of Driver Gene Information from Thoracic CT Images Based on SVM

Abstract

Molecular targeted therapies approved for the treatment of lung cancer have been recognized as having significantly higher response rates and less severe side effects in patients with driver gene mutations. However, genetic mutations are difficult to determine based on visual screening, and highly invasive bronchoscopy is recommended to patients. In this paper, we propose a method for detecting driver genetic information mutations from thoracic CT images with the aim of developing a CAD (Computer Aided Diagnosis) system to support physicians in making treatment decisions. This method uses clinical information of the patient and radiomics features extracted from two-dimensional tomographic CT images to perform supervised learning with SVM. After that, we perform two classes of mutation classifications and evaluation experiments to verify the effectiveness of the proposed method.