Computer-aided diagnosis for lung cancer

Methods for computer-aided diagnosis (CAD) of lung cancer have been develop ed for the analysis of chest radiographs and CT images. Computer methods ar e being applied to aid the radiologist in visualization of lesions, detecti on of pulmonary nodules in screening scans, and quantitative characterizati on of nodules in two and three dimensions. This review describes the method s currently used for the detection and characterization of pulmonary nodule s in both chest radiographs and low-resolution and high-resolution CT studi es. The current challenge for the early diagnosis of lung cancer is the det ection and characterization of small (diameter less than 1 cm) pulmonary no dules. Progress toward reproducible, quantitative measurement of these lesi ons is leading to advanced decision-making systems that aid the radiologist in making timely and accurate diagnoses.