Computer-aided diagnosis of the airways: beyond nodule detection

Although to date, the major impetus for the development of computer-assisted diagnosis (CAD) has been the detection of pulmonary nodules, CAD should properly be viewed as a potential tool for assisting radiologic interpretation of the entire gamut of chest diseases, including not just enhanced detection of disease but also characterization and quantification, ideally leading to improved patient management. The use of CAD to improve visualization of the airways using advanced computer techniques, including sophisticated methods for obtaining 3-dimensional segmentation of the central airways and, in particular, the development of virtual bronchoscopy has been recently studied. In this paper, the authors review the development of a specific series of CAD applications enabling automated identification and characterization of chronically inflamed airways. The advantages to the use of computer methodologies to quantify peripheral airway disease include reproducible visualization methods to display the location, severity, and extent of airway dilatation, bronchial wall thickening, and the presence of mucoid impacted airways. Currently, a number of semiquantitative global scoring systems have been proposed to assess disease extent and severity in patients with bronchiectasis. Unfortunately, with the exception of patients with cystic fibrosis, these are rarely if ever employed, largely owing to the considerable inconvenience of measuring individual airway dimensions and computing a global score. It is apparent that for this specific purpose, CAD may be ideally suited. Automated staging allows for more complete assessment of the entire bronchial tree while providing improved standardization and eliminating an otherwise tedious and time-consuming task.