Computer-Aided Detection system for nodule detection in lung CTs

A completely automated computer-aided detection (CAD) system for the selection of lung nodules in Computer Tomography (CT) images is presented. The system, based on Region Growing (RG) and Active Contour Model (ACM) algorithms, consists in three steps: 1) the lung parenchymal volume is segmented by means of a RG algorithm; nodules and vascular tree inside the lung are included through an ACM technique; 2) an RG algorithm is iteratively applied to the previously segmented volume in order to detect the candidate nodules; 3) a simple double-threshold cut and a neural network are applied to reduce the false positives (FPs). The system works on whole CTs, without the need for any manual selection. The CT database was recorded at the Pisa center of the ITALUNG-CT trial, the first Italian Randomized Controlled Trial for the screening of the lung cancer, following the Italung/I-ELCAP (International Early Lung Cancer Action Project) protocol. The detection rate of the system is 88.5% with 6.6 FPs/CT on 15 CT scans (about 4700 sectional images) with 26 nodules (15 internal and I I pleural). A reduction to 2.47 FPs/CT is achieved at 80% efficiency.