An Efficient Colon Segmentation method for Oral Contrast-Enhanced CT Colonography

A new method for fully automated segmentation of the colonic walls in volumetric CT data is proposed. Because each dataset requires long process time, this paper will focus on the development of an efficient segmentation method in half-sized volume data by an anatomical-oriented approach. The process utilizes global and local histograms of contrast enhanced fluids (CEF) to generate adaptive thresholds in oral contrast-enhanced CT for making two major binary masks. We applied a restricted "dilation" operation on an air binary mask for seeds generation and region growing. This method can surf all of colon lumen and extract all parts of it, even those might be submerged by CEF. The subjective and objective validation demonstrated that the error of leakage to extra colonic can be minimized. The procedures described could be the first stage in every multi stage colon lumen extraction and analysis