12 March 2010 Digital bowel cleansing for virtual colonoscopy with probability map
Author Affiliations +
Abstract
Virtual colonoscopy (VC) is a noninvasivemethod for colonic polyp screening, by reconstructing three-dimensional models of the colon using computerized tomography (CT). Identifying the residual fluid retained inside the colon is a major challenge for 3D virtual colonoscopy using fecal tagging CT data. Digital bowel cleansing aims to segment the colon lumen from a patient abdominal image acquired using an oral contrast agent for colonic material tagging. After removing the segmented residual fluid, the clean virtual colon model can be constructed and visualized for screening. We present a novel automatic method for digital cleansing using probability map. The random walker algorithm is used to generate the probability map for air (inside the colon), soft tissue, and residual fluid instead of segment colon lumen directly. The probability map is then used to remove residual fluid from the original CT data. The proposed method was tested using VC study data at National Cancer Institute at NIH. The performance of our VC system for polyp detection has been improved by providing radiologists more detail information of the colon wall.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Hong, Wei Hong, Feng Qiu, Feng Qiu, "Digital bowel cleansing for virtual colonoscopy with probability map", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 762341 (12 March 2010); doi: 10.1117/12.844281; https://doi.org/10.1117/12.844281
PROCEEDINGS
8 PAGES


SHARE
Back to Top