作者: Anna Jerebko , Sarang Lakare , Pascal Cathier , Senthil Periaswamy , Luca Bogoni
DOI: 10.1007/11866763_21
关键词: False positive paradox 、 Colonic Polyp 、 Artificial intelligence 、 Test set 、 Curvature 、 Quadratic classifier 、 Pattern recognition 、 Sensitivity (control systems) 、 Statistics 、 Spherical space 、 False positive rate 、 Mathematics
摘要: A novel approach for generating a set of features derived from properties patterns curvature is introduced as part computer aided colonic polyp detection system. The resulting sensitivity was 84% with 4.8 false positives per volume on an independent test 72 patients (56 polyps). When used in conjunction other features, it allowed the system to reach overall 94% positive rate 4.3 volume.