A Saliency-Based Unsupervised Method for Angioectasia Detection in Capsule Endoscopic Images

Abstract

Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia  from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch.  The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map.  In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.