A novel strategy to label abnormalities for Wireless Capsule Endoscopy frames sequence

Abstract

Wireless Capsule Endoscopy (WCE) is the most accurate, patient-friendly diagnostic tool that allows physicians to see the patient's whole gastrointestinal tract, especially the small intestine. However, reviewing capsule endoscopic video is a labor intensive task and very time consuming. Also the diagnosis process by WCE videos is not real-time. All above limitations motivate us to develop an approach to automatically detect the abnormalities in real time. In this paper we propose a novel strategy to detect abnormal frame for WCE videos. The key idea of the proposed strategy is to define the Frame Abnormality Index (FAI) using the ratio of training and testing data densities, where training dataset only consist of normal samples and testing dataset consist of both normal and abnormal samples. We select training and testing database from several WCE video segments to do our pilot experiment. Experimental results show that the proposed strategy achieves promising performances.