Multi-stage Neural Networks with Single-Sided Classifiers for False Positive Reduction and Its Evaluation Using Lung X-Ray CT Images

Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-stage convolutional neural networks that perform as single-sided classifiers filter out obvious nonnodules. Successively, a convolutional neural network trained with a balanced dataset calculates nodule probabilities. The proposed method achieved the sensitivity of 92.4% and 94.5% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, respectively.