Hybrid multiscale affine and elastic image registration approach towards wireless capsule endoscope localization

•A contribution to Wireless Capsule Endoscope localization using image-based methods.•An indicator of the Wireless Capsule Endoscope speed is obtained.•It captures both rigid-like and non-rigid deformations.•Superiority with respect to a multiscale affine registration.•Experimental tests with real videos demonstrate the good performance.

Wireless capsule endoscope (WCE) enables the visualization of the interior of the gastrointestinal (GI) tract. In particular it is very important for the examination of regions in the small bowel that cannot be reached by conventional endoscopy techniques. However, when an abnormality is found in WCE images of the small bowel, it is unknown how far is this abnormality from an anatomical reference point. The primary objective of the present paper is to give a contribution to WCE localization, using image-based methods. The main focus of this work is on the description of a hybrid multiscale affine and elastic image registration approach, its experimental application on WCE videos, and comparison with a multiscale affine registration. The proposed approach intends to track the WCE motion, by using the successive WCE frames that image the walls of the elastic small intestine. It includes registrations that capture both rigid-like and non-rigid deformations, due respectively to the rigid-like WCE movement and the elastic deformation of the small intestine originated by the GI peristaltic movement. Furthermore, the proposed approach enables the extraction of two parameters (scale and rotation) from which the relative displacement and orientation of the WCE inside the GI tract can be derived, via projective geometry. Under this approach an indicator of the WCE speed can be inferred, which can be clinically useful for video interpretation. The results of the experimental tests with real WCE video frames show the good performance of the proposed approach, when elastic deformations of the small intestine are involved in successive frames, and its superiority with respect to a multiscale affine image registration, which accounts for rigid-like deformations only and discards elastic deformations.