Detection of lymphangiectasia disease from wireless capsule endoscopy images with adaptive threshold

Wireless capsule endoscopy (WCE) is a great breakthrough for Gastrointestinal (GI) Tract diagnoses, and it can view the entire gastrointestinal tract, especially the small bowel, without invasiveness and sedation. However, a tough problem associated with this new technology is that too many images to be inspected by naked eyes cause a huge burden to physicians, so it is significant to find an automatic and intelligent diagnosis method to help the physicians. In this paper, a new automatic algorithm aimed for disease region detection of lymphangiectasia in CE images is proposed. This new approach mainly focuses on color feature, also a very effective clue used by physicians for diagnosis, to discriminate between normal region and abnormal region. We propose the luminance information of WCE images as the features due to the distinctiveness of the disease of lymphangiectasia. Then we use adaptive threshold classifier to verify the performances of the proposed feature extraction method and judge the status of the regions. Experimental results show that it is feasible to apply the proposed method to detect the disease of lymphangiectasia for WCE images.