ABSTRACT
Computed tomography (CT) is the imaging modality of choice for screening and staging of lung cancers (see Section III, Chapter 32). Low-dose chest CT is the preferred test for screening members of the asymptomatic population who are at risk of developing lung cancer. Often, early lung cancers originate as small sub-centimeter size lung nodules. Based on their location and size, as well as the experience of the radiologists, identification of small lung nodules on low dose chest CT can be a challenging task, and radiologists may benefit from the use of dedicated computer-aided detection (CAD) systems (see Section IV, Chapter 59). Here, we provide a description of the basic algorithmic components of a CAD system, of the methodological issues to consider in CAD performance evaluation, and of the potential impact of a CAD on the clinical radiology workflow. An overview of the CAD systems recently reported in the literature and a comparison of their performance are also provided. Open issues in this field of research are presented with the view of shortening the path to the release of accessible, fast, and high-performing lung CAD systems.
