An Automatic Bleeding Frame and Region Detection Scheme for Wireless Capsule Endoscopy Videos Based on Interplane Intensity Variation Profile in Normalized RGB Color Space.

Amit Kumar Kundu,Shaikh Anowarul Fattah,Mamshad Nayeem Rizve

doi:10.1155/2018/9423062

Abstract

Wireless capsule endoscopy (WCE) is an effective video technology to diagnose gastrointestinal (GI) disease, such as bleeding. In order to avoid conventional tedious and risky manual review process of long duration WCE videos, automatic bleeding detection schemes are getting importance. In this paper, to investigate bleeding, the analysis of WCE images is carried out in normalized RGB color space as human perception of bleeding is associated with different shades of red. In the proposed method, at first, from the WCE image frame, an efficient region of interest (ROI) is extracted based on interplane intensity variation profile in normalized RGB space. Next, from the extracted ROI, the variation in the normalized green plane is presented with the help of histogram. Features are extracted from the proposed normalized green plane histograms. For classification purpose, the K-nearest neighbors classifier is employed. Moreover, bleeding zones in a bleeding image are extracted utilizing some morphological operations. For performance evaluation, 2300 WCE images obtained from 30 publicly available WCE videos are used in a tenfold cross-validation scheme and the proposed method outperforms the reported four existing methods having an accuracy of 97.86%, a sensitivity of 95.20%, and a specificity of 98.32%.

Highlights

Bleeding is a common symptom for many gastrointestinal (GI) diseases, and bleeding detection has great clinical importance in diagnosing relevant diseases [1]
The objective of this paper is to develop an efficient scheme for detecting bleeding images and corresponding bleeding regions based on precise region of interest (ROI) detection in normalized RGB color plane
An efficient ROI extraction scheme is proposed based on rgb domain in a wireless capsule endoscopy (WCE) image

Summary

Introduction

Bleeding is a common symptom for many gastrointestinal (GI) diseases, and bleeding detection has great clinical importance in diagnosing relevant diseases [1] Conventional endoscopic techniques, such as gastroscopy and colonoscopy, face problem in demonstrating small intestine and cause a lot of pain. Automated scheme to detect bleeding has received much attention by several researchers In this regard, the suspected blood indicator (SBI), a software delivered along with secondgeneration capsule, is reported to be one of the very first attempts to detect WCE bleeding images with moderate accuracy [5]. The SBI does not reduce the required interpretation time of WCE videos, which is its main goal [6] This motivated the researchers to propose new algorithms for automatic bleeding detection in WCE videos. In [9], a probabilistic neural network (PNN) is employed for bleeding

Objectives

Findings

Discussion

Conclusion