Advanced Visualization for Virtual Endoscopy from Wireless Capsule Endoscopy Video

초록

Wireless capsule endoscopy (WCE) has been intensively researched recently due to its convenience for diagnosis and extended detection coverage of some diseases. In spite of the benefits of close examination, WCE based test has a barrier for quick diagnosis such that a trained diagnostician must examine a huge amount of images for close investigation, normally over 2 hours. The main purpose of our work is to present a novel machine vision approach to reduce diagnosis time by automatically detecting duplicated recordings caused by backward camera movement and to aid diagnosis by the video reconstruction. Our method consists of optical-flow-based methods to detect images containing near-duplicate spatial coverage caused by continuously switching backward and forward ego-motions due to peristalses and template matching based methods to compensate for ego-motion with panning or rotation. Our experiment shows 9.9% duplicated image removal ratio in the small intestine.