Organic Boundary Location Based on Color-Texture of Visual Perception in Wireless Capsule Endoscopy Video.

Chengliang Wang,Zhuo Luo,Jianying Bai,Xiaoqi Liu,Guobin Liao

doi:10.1155/2018/3090341

Abstract

This paper addresses the problem of automatically locating the boundary between the stomach and the small intestine (the pylorus) in wireless capsule endoscopy (WCE) video. For efficient image segmentation, the color-saliency region detection (CSD) method is developed for obtaining the potentially valid region of the frame (VROF). To improve the accuracy of locating the pylorus, we design the Monitor-Judge model. On the one hand, the color-texture fusion feature of visual perception (CTVP) is constructed by grey level cooccurrence matrix (GLCM) feature from the maximum moments of the phase congruency covariance and hue-saturation histogram feature in HSI color space. On the other hand, support vector machine (SVM) classifier with the CTVP feature is utilized to locate the pylorus. The experimental results on 30 real WCE videos demonstrate that the proposed location method outperforms the related valuable techniques.

Highlights

Wireless capsule endoscopy (WCE) was invented by a group of researchers in Baltimore in 1989 and introduced by Given Imaging Inc. as a commercial tool [1]
(3) The color-texture fusion feature of visual perception (CTVP) feature is constructed by grey level cooccurrence matrix (GLCM) feature from the maximum moments of the phase congruency covariance and hue-saturation histogram feature in HSI color space, which is better to express the difference between stomach images and small intestine images than other selected features [11, 12]
The better performance of using valid region of the frame (VROF) regions can be explained by the fact that it is necessary to reduce the negative influence brought by gastric juice, shadows, excessive bright regions, and bubbles

Summary

Introduction

Wireless capsule endoscopy (WCE) was invented by a group of researchers in Baltimore in 1989 and introduced by Given Imaging Inc. as a commercial tool [1]. Yuan and Meng [5] and Karargyris and Bourbakis [6] just detect the lesion images in the small intestine, but they both manually select the part of WCE video about the small intestine for avoiding the disturbance of other organs It is a time-consuming and laborious task to locate the organic boundaries artificially. They all firstly find the approximate positions of organic boundary and refine the boundary These two approaches are both time-consuming tasks because they need to compute almost all the images about the stomach and the small intestine in WCE videos. (3) The CTVP feature is constructed by grey level cooccurrence matrix (GLCM) feature from the maximum moments of the phase congruency covariance and hue-saturation histogram feature in HSI color space, which is better to express the difference between stomach images and small intestine images than other selected features [11, 12]

Materials and Methods

Monitor-Judge Model for Pyloric Position

Results and Discussion

Conclusions