A 3D nodule candidate detection method supported by hybrid features to reduce false positives in lung nodule detection

Lungs cancer is a fatal disease. However, its early detection increases the chances of survival among patients. An automated nodule detection system provides the second opinion to radiologists in early diagnosis. In this paper, an automated technique for nodule detection and classification is presented. Firstly, the lung region is extracted on the basis of the optimal gray level threshold. In the next phase, a novel hybrid 3D nodule candidate detection method is presented, comprises of Active Contour Model (ACM), 3D neighborhood connectivity and geometric properties based rules. A hybrid feature vector is created, by combining geometric texture and Histogram of Oriented Gradient reduced by Principle Component Analysis (HOG-PCA) features, for each nodule candidate. After feature extraction, classification is performed by applying four different classifiers including k-Nearest Neighborhood (k-NN), Naive Bayesian, Support Vector Machine (SVM) and AdaBoost. The evaluation is performed over Lung Image Database Consortium (LIDC) database. It is evident that AdaBoost has outperformed all other classifiers regarding accuracy, sensitivity, specificity and FPs/scan. Moreover, the proposed technique has shown significantly better results as compared to other existing methods reported in the literature.