Title :
Learning disease severity for capsule endoscopy images
Author :
Kumar, R. ; Rajan, P. ; Bejakovic, S. ; Seshamani, S. ; Mullin, G. ; Dassopoulos, T. ; Hager, G.
Author_Institution :
Dept. of Comput. Sci., Johns Hopkins Univ., Baltimore, MD, USA
fDate :
June 28 2009-July 1 2009
Abstract :
Wireless capsule endoscopy (CE) is increasing being used to assess several gastrointestinal(GI) diseases and disorders. Current clinical methods are based on subjective evaluation of images. In this paper, we develop a method for ranking lesions appearing in CE images. This ranking is based on pairwise comparisons among representative images supplied by an expert. With such sparse pairwise rank information for a small number of images, we investigate methods for creating and evaluating global ranking functions. In experiments with CE images, we train statistical classifiers using color and edge feature descriptors extracted frommanually annotated regions of interest. Experiments on a data set using Crohn´s disease lesions for lesion severity are presented with the developed ranking functions achieve high accuracy rates.
Keywords :
biological organs; biomedical optical imaging; diseases; edge detection; endoscopes; feature extraction; image classification; image colour analysis; medical image processing; statistical analysis; Crohn disease lesions; capsule endoscopy images; color feature descriptors; disease severity; edge feature descriptors; gastrointestinal diseases; gastrointestinal disorders; global ranking functions; lesion severity; lesions; sparse pairwise rank information; statistical classifiers; wireless capsule endoscopy; Batteries; Biomedical imaging; Computer science; Data mining; Diseases; Endoscopes; Feature extraction; Hospitals; Lesions; Medical diagnostic imaging; Capsule Endoscopy; Disease Severity; Ordinal Regression; Statistical Classification;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-3931-7
Electronic_ISBN :
1945-7928
DOI :
10.1109/ISBI.2009.5193306