An automated pulmonary nodule detection system is necessary to help radiologist to identify and detect the nodules at early stage. In this paper, a novel pulmonary nodule detection system is proposed using Artificial Neural Networks (ANN) based on hybrid features consist of 2D and 3D Geometric and Intensity based statistical features. The lung volume is segmented using thresholding, 3D connected component labeling, contour correction and morphological operators. The candidate nodules are extracted and pruned based on the rules that are built using characteristics of nodules. The 2D and 3D Geometric features and Intensity Based Statistical features are extracted and used to train a Neural Network. The proposed Computer-Aided Diagnostic (CAD) system is tested and validated using standard dataset of Lung Image Consortium Database (LIDC). The results obtained from proposed CAD system are good as compared to existing CAD systems. The sensitivity of 96.95% is achieved with accuracy of 96.68%.
Digital Object Identifier (DOI)
Akram, Sheeraz; Younus Javed, Muhammad; Qamar, Usman; Khanum, Aasia; and Hassan, Ali
"Artificial Neural Network based Classification of Lungs Nodule using Hybrid Features from Computerized Tomographic Images,"
Applied Mathematics & Information Sciences: Vol. 09:
1, Article 31.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol09/iss1/31