Classification of Ulcerative Colitis Severity in Colonoscopy Videos Using Vascular Pattern Detection

摘要

Endoscopic measurement of ulcerative colitis (UC) severity is important since endoscopic disease severity may better predict future outcomes in UC than symptoms. However, it is difficult to evaluate the endoscopic severity of UC objectively because of the non-uniform nature of endoscopic features associated with UC, and large variations in their patterns. In this paper, we propose a method to classify UC severity in colonoscopy videos by detecting the vascular (vein) patterns which are defined specifically in this paper as the amounts of blood vessels in the video frames. To detect these vascular patterns, we use Convolutional Neural Network (CNN) and image preprocessing methods. The experiments show that the proposed method for classifying UC severity by detecting these vascular patterns increases classification effectiveness significantly.