PT Unknown
AU Jorge Bernal
   F. Javier Sanchez
   Fernando Vilariño
TI Current Challenges on Polyp Detection in Colonoscopy Videos: From Region Segmentation to Region Classification. a Pattern Recognition-based Approach.ased Approach
BT 2nd International Workshop on Medical Image Analysis and Descriptionfor Diagnosis Systems
PY 2011
BP 62
EP 71
DE Medical Imaging; Colonoscopy; Pattern Recognition; Segmentation; Polyp Detection; Region Description; Machine Learning; Real-time.
AB In this paper we present our approach on real-time polyp detection in colonoscopy videos. Our method consists of three stages: Image Segmentation, Region Description and Image Classification. Taking into account the constraints of our project, we introduce our segmentation system that is based on the model of appearance of the polyp that we have defined after observing real videos from colonoscopy processes. The output of this stage will ideally be a low number of regions of which one of them should cover the whole polyp region (if there is one in the image). This regions will be described in terms of features and, as a result of a machine learning schema, classified based on the values that they have for the several features that we will use on their description. Although we are still on the early stages of the project, we present some preliminary segmentation results that indicates that we are going in a good direction.
ER