A New Algorithm of Electronic Cleansing for Weak Faecal-Tagging CT Colonography

摘要

CT Colonography (CTC) has emerged as a mainstream clinical practice of colonic cancer screening and diagnosis. One of the most critical problems is to increase compliance with CTC examinations via minimal bowel preparation (i.e., weak faecal-tagging), which nevertheless causes much lower signal-noise-ratio than conventional preparation. In this paper, we present a new algorithm pipeline of electronically cleansing tagging materials in CTC under reduced oral contrast dose. Our method has the following steps: 1, robust structure parsing to generate a list of volume regions of interest (ROIs) of tagging material (avoiding bone erosion); 2, effectively locating local tagging-air (AT) transitional surface regions; 3, a novel discriminative-generative algorithm to learn the higher-order image appearance model in AT using 3D Markov Random Fields (MRF); 4, accurate probability density function based voxel labeling corresponding to semantic classes. Validated on 26 weak faecal-tagging CTC cases from 3 medical sites, our method yields better visualization clarity and readability compared with the previous approach. The whole system computes efficiently (e.g., ＜ 40 seconds for CT images of 512 × 512 × 1000+).