A unified approach for detection, visualization, and identification of lung abnormalities in chest spiral CT scans

Abstract This research aims at developing a fully automatic Computer-Assisted Diagnosis (CAD) system for lung cancer screening using chest spiral CT scans. This paper presents two novel approaches for segmentation of the lung tissues from the surrounding structures in the chest cavity, and detection of the abnormalities in the lung tissues. The segmentation algorithm is hierarchical. The first step is to isolate the background from the chest cavity. The second step is to isolate the lungs from the surrounding structures (e.g., ribs, liver, and other organs that may appear in chest CT scans) by using Gibbs–Markov Random Field (GMRF). The third step is to isolate the abnormality (lung nodules), arteries, vines, bronchi, and bronchioles from the normal tissues. Finally, the abnormalities in the lungs are detected by using adaptive template matching; its parameters (mean, variance…) are estimated from the given data. In order to increase the speed of detecting lung nodules, we use genetic algorithms (GAs) to determine the target position in the observed image and to select an adequate template image from several reference patterns.