Computer-aided Diagnosis Scheme for Detection of Polyps at CT Colonography

摘要: Colon cancer is one of the leading causes deaths in United States. However, most colon cancers can be prevented if precursor colonic polyps are detected and removed. An advanced computer-aided diagnosis (CAD) scheme was developed for automated detection at computed tomographic (CT) colonography. A region encompassing wall extracted from an isotropic volume data set obtained by interpolating CT colonographic scans along axial direction. Polyp candidates with computation three-dimensional (3D) geometric features that characterize polyps, followed extraction hysteresis thresholding fuzzy clustering using these features. The number false-positive findings reduced extracting 3D texture polyp applying quadratic discriminant analysis to candidates. This CAD applied 71 patients who underwent colonography, 14 whom had colonoscopically confirmed (n = 21). At by-patient analysis, sensitivity 100%, average rate 2.0 per patient. by-polyp 90% same rate. permits accurate suspicious lesions thus has potential reduce radiologists' interpretation time improve their diagnostic accuracy