A method for bleeding detection in endoscopy images using SVM / 中国医疗器械杂志

ABSTRACT

Because the huge number of images of the digestive tract by Wireless Capsule Endoscopy (WCE) are left to the medical personnels detected by their eyes, huge burden leaves to doctors. This article provides a classification of method based on SVM (Support Vector Machine) for the capsule endoscopy bleeding intelligent recognition. We created a new kind of feature parameter, and the experiment result can reach 83% specificity and 94% sensitivity.