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

摘要

Lung nodule classification is a class imbalanced problem because nodules axe found in 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 perform as single-sided classifiers to filter out obvious non-nodules. Successively, a convolutional neural network trained with a balanced data set 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.