Designing a new CAD system for pulmonary nodule detection in High Resolution Computed Tomography (HRCT) images

Lung diseases and lung cancer are among the most dangerous diseases with high mortality in both men and women. Lung nodules are abnormal pulmonary masses and are among major lung symptoms. A Computer Aided Diagnosis (CAD) system may play an important role in accurate and early detection of lung nodules. This article presents a new CAD system for lung nodule detection from chest computed tomography (CT) images. Twenty-five adult patients with lung nodules in their CT scan images presented to the National Research Institute of Tuberculosis and Lung Disease, Masih Daneshvari Hospital, Tehran, Iran in 2011-2012 were enrolled in the study. The patients were randomly assigned into two experimental (9 female, 6 male, mean age 43±5.63 yrs) and control (6 female, 4 male, mean age 39±4.91 yrs) groups. A fully-automatic method was developed for detecting lung nodules by employing medical image processing and analysis and statistical pattern recognition algorithms. Using segmentation methods, the lung parenchyma was extracted from 2-D CT images. Then, candidate regions were labeled in pseudo-color images. In the next step, some features of lung nodules were extracted. Finally, an artificial feed forward neural network was used for classification of nodules. Considering the complexity and different shapes of lung nodules and large number of CT images to evaluate, finding lung nodules are difficult and time consuming for physicians and include human error. Experimental results showed the accuracy of the proposed method to be appropriate (P<0.05) for lung nodule detection.