Resumen
Epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS) are the most common driver genes in non-small cell lung cancer patients. However, frequent gene mutation testing raises a potential risk of cancer metastasis. In our paper, a Mut-SeResNet model based on the ResNet network that incorporated a residual block and attention mechanism was proposed to solve the performance degradation problem caused by a deepening of the network. We introduced a residual structure and extracted small differences between different levels to enhance the feature learning ability. The squeeze and excitation attention mechanism was adapted to fully extract the dependence between different channels of the feature image, and it calibrated the channel feature information. We used the dataset of 363 patients that were collected from collaborating hospitals to train our Mut-SeResNet model. The prediction accuracy for EGFR and KRAS mutations was 89.7% and 88.3%, respectively, with a loss accuracy of 6.4% and 9.2%, respectively. The results showed that the model provided a non-invasive and easy-to-use method to improve the accuracy and stability of clinical diagnosis.