Detection of colon wall outer boundary and segmentation of the colon wall based on level set methods

Virtual colonoscopy (VC) has become a more prevalent and accepted method to diagnosis colorectal cancer. An essential element to detecting cancerous polyps using VC in conjunction with computer-aided detection is the accurate segmentation of the colon wall. While the inner boundary of the colon wall, the lumen-mucosal boundary, has often been the focus of previous colon segmentation work, detection of the outer wall, the serosal tissue boundary, allows for the segmentation of the colon wall, which is useful in determining both potential polyps, muscular hypertrophy and diverticulitis of the colon. Unfortunately, automatic determination of the outer colon wall position often is difficult due to the low contrast between CT attenuation values of the colon wall and the surrounding fat tissue. We have developed a level set based method to determine from a CT colonography (CTC) scan the location of the colon serosal tissue boundary. After determining this location, the algorithm segments the entire colon wall at subvoxel accurate precision. The algorithm has been validated on several CTC datasets.