Pulmonary nodule classification using feature and ensemble learning-based fusion techniques

Abstract

The Pulmonary nodule indicates the presence of lung cancer. The deep convolutional neural networks (DCNNs) have been widely used to classify the pulmonary nodule as benign or malignant. However, an individual learner usually performs unsatisfactorily due to limited response space, incorrect selection of hypothesis space, or falling into local minimums. To investigate these issues, we propose ensemble learners fusion techniques based on averaging of prediction score and maximum vote score (MAX-VOTE). First, the support vector machine (SVM) and AdaBoostM2 machine learning algorithms are trained on the deep features from DCNNs. The results of both classifiers are fused separately based on averaging of the prediction score. Secondly, the feature fusion technique is developed by fusing the feature of three DCNNs (AlexNet, VGG-16 and VGG-19) through predefined rules. After that, the SVM and AdaBoostM2 are trained on fused features independently to build ensemble learners by fusing the multiple DCNN learners. The predictions of all DCNN learners are fused based on the MAX-VOTE. The results show that the ensemble learners based MAX-VOTE technique yields better performance out of twelve single learners for binary class classification of pulmonary nodules. The proposed fusion techniques are also tested for multi-class classification problem. The SVM based feature fusion technique performs better as compared to all the implemented and the state-of-the-art techniques. The achieved maximum accuracy, AUC and specificity scores are 96.89%±0.25, 99.21%±0.10 and 97.70%±0.21, respectively.