Computer-aided detection (CAD) for CT colonography: a tool to address a growing need.

摘要: Colorectal cancer is the third most common in both men and women. It estimated that 2004, nearly 147 000 cases of colon rectal will be diagnosed USA, approximately 57 000 people would die from disease; however, only 44% eligible population undergoes any type colorectal screening. Many reasons have been identified for non-compliance, with key ones being patient comfort, bowel preparation cost. Virtual colonoscopy derived computed tomography (CT) images gaining broader acceptance as a screening method neoplasia. Our research suggests computer-aided detection (CAD) second reader has great potential improving polyp detection. The ColonCAD prototype presented this paper was developed tested on representative variability quality true clinical practice. Results study 150 patients demonstrate that: algorithm generalises well: sensitivity polyps ⪖ge;6 mm o...