Deep learning based automated epidermal growth factor receptor and anaplastic lymphoma kinase status prediction of brain metastasis in non-small cell lung cancer

The aim of this study was to investigate the feasibility of developing a deep learning (DL) algorithm for classifying brain metastases from non-small cell lung cancer (NSCLC) into epidermal growth factor receptor ( ) mutation and anaplastic lymphoma kinase ( ) rearrangement groups and to compare the accuracy with classification based on semantic features on imaging. Data set of 117 patients was analysed from 2014 to 2018 out of which 33 patients were positive, 43 patients were positive and 41 patients were negative for either mutation. Convolutional neural network (CNN) architecture efficient net was used to study the accuracy of classification using T1 weighted (T1W) magnetic resonance imaging (MRI) sequence, T2 weighted (T2W) MRI sequence, T1W post contrast (T1post) MRI sequence, fluid attenuated inversion recovery (FLAIR) MRI sequences. The dataset was divided into 80% training and 20% testing. The associations between mutation status and semantic features, specifically sex, smoking history, mutation and rearrangement status, extracranial metastasis, performance status and imaging variables of brain metastasis were analysed using descriptive analysis [chi-square test (χ )], univariate and multivariate logistic regression analysis assuming 95% confidence interval (CI). In this study of 117 patients, the analysis by semantic method showed 79.2% of the patients belonged to positive were non-smokers as compared to double negative groups ( = 0.03). There was a 10-fold increase in positivity as compared to positivity in ring enhancing lesions patients ( = 0.015) and there was also a 6.4-fold increase in positivity as compared to double negative groups in meningeal involvement patients ( = 0.004). Using CNN Efficient Net DL model, the study achieved 76% accuracy in classifying rearrangement and mutations without manual segmentation of metastatic lesions. Analysis of the manually segmented dataset resulted in improved accuracy of 89% through this model. Both semantic features and DL model showed comparable accuracy in classifying mutation and rearrangement. Both methods can be clinically used to predict mutation status while biopsy or genetic testing is undertaken.