Ensemble learning approaches to classification of pulmonary nodules

Lung cancer is one of the primary causes of cancer-related death worldwide. A computer-aided detection (CAD) can help radiologists by offering a second opinion and making the whole process faster at an early level. In this study, we propose a new classification approach for pulmonary nodule detection from CT imagery by using morphological features of nodule patterns. Ensemble learning approaches are used for classification process and overall detection performance is evaluated. Results are compared to similar techniques in the literature by using standard measures. The performance of the proposed system with random forest based on ensemble learning approaches results in an overall accuracy of 98.7 % with a sensitivity of 100 % and specificity of 97.3 % in training data set and an overall accuracy of 80.7 % with a sensitivity of 80.7 % and specificity of 80.6 % in testing dataset.