SUMMARY
Due to the high incidence of the lung cancer all over the world, computer-aided detection (CAD) systems play an important role in screening. Classification in CAD systems have to deal with highly imbalanced datasets composed by actual nodules and non-nodules structures. The application of data balancing techniques helps the training process of the classifiers making the generation of the classification rules more effective. The purpose of this paper is to compare the performance of different data balancing techniques applied to the classification of lung nodules. According to the reviewed literature, this is the first time that different data balancing methods are evaluated on the problem of lung nodule detection using a large data set. A web-based framework was used to evaluate the different methods applied to a classical CAD system (ETROCAD) presented in the LUNA16 Challenge. In the experiments, data balance using SMOTE and SMOTE-TL lead to the best results, with a score of 0.760 and 0.759 respectively, in comparison to 0.748 when not balancing the data. At the time of writing this paper, the SMOTE-based ETROCAD system have the best score among all the classical systems using handcrafted features in LUNA16 web sit.