Title :
Intestinal event segmentation for endoluminal video analysis
Author :
Drozdzal, M. ; Vitria, J. ; Segui, S. ; Malagelada, C. ; Azpiroz, F. ; Radeva, P.
Author_Institution :
Comput. Vision Center (CVC), Barcelona, Spain
Abstract :
In this paper, we tackle the problem of unsupervised segmentation of intestinal events using various motility descriptors extracted from the endoluminal video. The segments of constant intestinal activity are detected with a robust statistical test that is based on Hoeffding´s inequality. The qualitative analysis of the results shows that the segments adjust well to the motility information and thus, this segmentation can constitute basic units for higher-level motility description.
Keywords :
biological tissues; biomedical optical imaging; capacitive sensors; endoscopes; image segmentation; image sequences; medical signal processing; motion estimation; patient diagnosis; video signal processing; Hoeffding inequality-based statistical test; constant intestinal activity segments; endoluminal video analysis; endoluminal video-extracted descriptors; higher-level motility description; intestinal activity segment detection; intestinal event segmentation; intestinal motility information; motility descriptors; robust statistical test; unsupervised segmentation; Endoscopes; Image segmentation; Intestines; Partitioning algorithms; Robustness; Streaming media; Wireless communication; Intestinal events; WCE; multivariate data stream; unsupervised segmentation;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7025729
