Segmentation and Volumetric Analysis of Colon Wall for Detection of Flat Polyp Candidates via CT Colonography

Accurate segmentation and volumetric analysis of colon wall is essential to advance computer-aided detection (CAD) of colonic polyps in computed tomography colonography (CTC). Due to their limited geometric information, detection of flat polyps is very difficult in both optical colonoscopy and CTC. In this paper, we present a new framework of segmentation and volumetric analysis of colon wall for improving detection of flat polyps. First, partial volume (PV) effects around the inner mucous membrane of the colon were reserved through our PV based electronic colon cleansing. PV information was further used to guide colon wall segmentation as well as to establish the starting point of iso-potential surfaces for colon wall thickness measures. Then, we employed a dual level set competition model to simultaneously segment both inner and outer colon wall by taking into account the mutual interference between two borders. We further conducted volumetric analysis of the dynamic colon wall information and built four layer of iso-potential surfaces which represent the intrinsic anatomical information of colon wall. We built a unique point-to-point path starting from the very beginning of the mucous membrane of the colon. As flat polyps are plaque-like lesions raised less than 3mm from the colonic mucosa layer, inclusion of PV effects shall bring us the fine information about flat polyps, thus improving the detection performance. The proposed framework was validated on patient CTC scans with flat polyps. Experimental results demonstrated that the framework is very promising towards detection of colonic flat polyps via CTC.