EGFR and KRAS mutation prediction on lung cancer through medical image processing and artificial intelligence

Abstract

Lung cancer causes more deaths globally than any other type of cancer. To determine the best treatment, detecting EGFR and KRAS mutations is of interest. However, non-invasive ways to obtain this information are not available. In this study, an ensemble approach is applied to increase the performance of EGFR and KRAS mutation prediction from CT images using a small dataset. A new voting scheme, Selective Class Average Voting (SCAV) is proposed and its performance is assessed both for machine learning models and Convolutional Neural Networks (CNNs). For the EGFR mutation, in the machine learning approach, there was an increase in the Sensitivity from 0.66 to 0.75, and an increase in AUC from 0.68 to 0.70. With the deep learning approach an AUC of 0.846 was obtained with custom CNNs, and with SCAV the Accuracy of the model was increased from 0.80 to 0.857. Finally, when combining the best Custom and Pre-trained CNNs using SCAV an AUC of 0.914 was obtained. For the KRAS mutation both in the machine learning models (0.65 to 0.71 AUC) and the deep learning models (0.739 to 0.778 AUC) a significant increase in performance was found. This increase was even greater with Ensembles of Pre-trained CNNs (0.809 AUC). The results obtained in this work show how to effectively learn from small image datasets to predict EGFR and KRAS mutations, and that using ensembles with SCAV increases the performance of machine learning classifiers and CNNs.