This paper details the development of a novel method for automatic segmentation of collapsed colon lumen based on prior knowledge of colon geometrical features and anatomical structure. After the removal of the surrounding air voxels and lungs from the volumetric Computed Tomography (CT) data, labeling was performed to to detect the remaining air voxel regions inside the CT data. Volume by length analysis, orientation, length, and points, geometrical position in the volumetric data, the gradient of centreline of each labeled air region were used as geometrical features to automatically segment the colon in CT data. The proposed method was validated by using 115 datasets. Collapsed colon surface detection was always higher than 95% with an average of 1.07% extra colonic surface inclusion . When the devised segmentation technique was applied to well-distended colon surface the colon detection was close to 100%