Digital bowel cleansing for virtual colonoscopy with probability map

Wei Hong; Feng Qiu

doi:10.1117/12.844281

12 March 2010 Digital bowel cleansing for virtual colonoscopy with probability map

Wei Hong, Feng Qiu

Proceedings Volume 7623, Medical Imaging 2010: Image Processing; 762341 (2010) https://doi.org/10.1117/12.844281
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

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.

Citation Download Citation

Wei Hong and Feng Qiu "Digital bowel cleansing for virtual colonoscopy with probability map", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 762341 (12 March 2010); https://doi.org/10.1117/12.844281

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available