作者: Dongqing Chen , M. Sabry Hassouna , Aly A. Farag , Robert Falk
DOI: 10.1007/11812715_47
关键词:
摘要: Computed Tomography Colonography has been proved to be a valid technique for detecting and screening colorectal cancers. In this paper, we present framework colonic polyp detection segmentation. Firstly, propose use four different geometric features detection, which include shape index, curvedness, sphericity ratio the absolute value of inner product maximum principal curvature gradient vector flow. Then, bias-corrected fuzzy c-mean algorithm flow based deformable model Finally, measure overlap between manual segmentation test accuracy our frame work. The quantitative experiment results have shown that average is 85.17%±3.67%.