13 March 2013 Localizing and segmenting Crohn's disease affected regions in abdominal MRI using novel context features
Author Affiliations +
Proceedings Volume 8669, Medical Imaging 2013: Image Processing; 86693K (2013) https://doi.org/10.1117/12.2006698
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States
Increasing incidence of Crohn’s disease (CD) in the Western world has made its accurate diagnosis an important medical challenge. The current reference standard for diagnosis, colonoscopy, is time consuming and invasive due to which Magnetic resonance imaging (MRI) has emerged as the preferred non-invasive procedure over colonoscopy. Current MRI approaches rely on extensive manual segmentation for an accurate analysis thus limiting their effectiveness. We propose a supervised learning method for the localization and segmentation of regions in abdominal MR images that have been affected by CD. Higher order statistics from intensity and texture are used with context information to distinguish between diseased and normal regions. Particular emphasis is laid on a novel measure to derive context information. Experiments on real patient data show that our features achieve high sensitivity and can successfully segment out the pixels belonging to CD affected regions.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dwarikanath Mahapatra, Dwarikanath Mahapatra, Peter J. Schüffler, Peter J. Schüffler, Jeroen A. W. Tielbeek, Jeroen A. W. Tielbeek, Franciscus M. Vos, Franciscus M. Vos, Joachim M. Buhmann, Joachim M. Buhmann, } "Localizing and segmenting Crohn's disease affected regions in abdominal MRI using novel context features", Proc. SPIE 8669, Medical Imaging 2013: Image Processing, 86693K (13 March 2013); doi: 10.1117/12.2006698; https://doi.org/10.1117/12.2006698

Back to Top