.png)
In this paper, we present a computer aided diagnosis (CAD) system for lung nodule detection in computed tomography (CT) images. Here, the density values of pixels in CT image slices are used and scanning the pixels in 8 directions is evaluated. By using various thresholds while scanning the pixels, lung nodule shapes and parts of the normal structure shapes (blood vessels, bronchus etc.) are found. All shapes are labeled using connected component labeling (CCL). Two rules are used to distinguish lung nodules from normal structures. In the first rule, the euclidean distance of the shape, and in the second rule the regularity which is the ratio of euclidean distance to thickness of the shape is considered. The performance of the system is evaluated using a test set which contains totally 35 normal and abnormal images, with 61 nodules. When results are compared with the second look reviews of a chest radiologist, it is seen that the system achieved 89% sensitivity with 0.457 false positives (FPs) per image. The proposed system which obtains high sensitivity with acceptable low number of false positives per image, may improve the computerized analysis of lung CTs and early diagnosis of lung nodules.