PT Chapter
AU Debora Gil
   F. Javier Sanchez
   Gloria Fernandez Esparrach
   Jorge Bernal
TI 3D Stable Spatio-temporal Polyp Localization in Colonoscopy Videos
BT Computer-Assisted and Robotic Endoscopy. Revised selected papers of Second International Workshop, CARE 2015, Held in Conjunction with MICCAI 2015
PY 2015
BP 140
EP 152
VL 9515
DI 10.1007/978-3-319-29965-5_14
DE Colonoscopy; Polyp Detection; Polyp Localization; Region Extraction; Watersheds
AB Computational intelligent systems could reduce polyp miss rate in colonoscopy for colon cancer diagnosis and, thus, increase the efficiency of the procedure. One of the main problems of existing polyp localization methods is a lack of spatio-temporal stability in their response. We propose to explore the response of a given polyp localization across temporal windows in order to selectthose image regions presenting the highest stable spatio-temporal response.Spatio-temporal stability is achieved by extracting 3D watershed regions on thetemporal window. Stability in localization response is statistically determined by analysis of the variance of the output of the localization method inside each 3D region. We have explored the benefits of considering spatio-temporal stability in two different tasks: polyp localization and polyp detection. Experimental results indicate an average improvement of 21:5% in polyp localization and 43:78% in polyp detection.
ER