In situ analysis of capsule endoscopy images and preliminary results

Capsule endoscopy has been proved efficient in examining the small intestine. A lot of work has been devoted to the study of capsule videos to assist the diagnosis. Different from previous approaches which worked off-line and couldn´t be applied in active capsule controls, in this paper we proposed an in situ capsule video analysis method, which operates in real-time and provides the first event detection-based scheme for capsule techniques. Specifically, first we established a theoretical computing framework. The method addresses two key points: one is to merge the surgeon´s expertise into the system, and the other is to identify unusual events. Then we evaluated the method by some empirical experiments. The preliminary results verified the usefulness of the method.