Modeling of the Movement of the Endoscopy Capsule inside G.I. Tract based on the Captured Endoscopic Images

Wireless capsule endoscopy (WCE) is a noninvasive technology that provides excellent images of the intestinal lumen as the capsule moving along in the gastrointestinal (G.I.) tract. However, the biggest drawback of this technology is its incapability of localizing the capsule when an abnormality is found by the video source. Existing localization methods based on radio frequency (RF) and magnetic field suffer a great error due to the non-homogeneity of the human body and uncertainly of the movement of the endoscopic capsule. To complement the existing localization techniques, in this paper, we developed a series of image processing and visualization based algorithms to model the movement of the endoscopic capsule. First, a 3D map of the G.I. tract is generated to navigate the transition of the capsule. Then, by comparing the local similarity and feature matching between the consecutive frames, the speed and rotation angels of the capsule can be roughly estimated. Finally, by mapping the pattern of the capsule’s movement onto the 3D G.I. tract map, we are able to simulate the entire transition of the endoscopic capsule in the 3D space. Empirical results show that the proposed method has a good estimation of the capsule’s movement.