Segmenting Reddish Lesions in Capsule Endoscopy Images Using a Gastrointestinal Color Space

2014 ◽  
Author(s):  
Hai Vu ◽  
Tomio Echigo ◽  
Yuma Imura ◽  
Yukiko Yanagawa ◽  
Yasushi Yagi
Keyword(s):  
Capsule Endoscopy ◽  
Color Space

scholarly journals Bile pigment in small-bowel water content may reflect bowel habits: a retrospective analysis of a capsule endoscopy imaging series

2020 ◽  
Author(s):  
Taiki Aoyama ◽  
Akira Fukumoto ◽  
Kenjiro Shigita ◽  
Naoki Asayama ◽  
Shinichi Mukai ◽  
...  
Keyword(s):  
Bile Acid ◽  
Small Bowel ◽  
Water Content ◽  
Capsule Endoscopy ◽  
Color Space ◽  
Bile Pigment ◽  
Bile Pigments ◽  
Normal Bowel ◽  
Bowel Habits ◽  
The Impact

Abstract Background: Pigmented bile salts darken the small-bowel lumen and are present with bile acid, which is involved in the development of bowel habits. The small-bowel water content (SBWC) in the ileum could represent the colonic environment, but no studies have focused on this feature. However, measurement of crude SBWC can be challenging because of the technical difficulty of the endoscopic approach without preparation. Our aim was to evaluate optically active bile pigments in the SBWC of patients with abnormal bowel habits using capsule endoscopy (CE) to investigate the impact of bile acid on bowel habits. Methods: The study population included 37 constipated patients, 20 patients with diarrhea, and 77 patients with normal bowel habits who underwent CE between January 2015 and May 2018. Patients with secondary abnormal bowel habits were excluded. In addition to conventional imaging, we used flexible spectral imaging color enhancement (FICE) setting 1 imaging, in which the effects of bile pigments on color are suppressed. Intergroup color differences of SBWC in the ileum (ΔE) were evaluated from conventional and FICE setting 1 images. Color values were assessed using the CIE L*a*b* color space. Differences in SBWC lightness (black to white, range 0–100) were also evaluated. Results: The ΔE values from the comparison of conventional images between patients with constipation and with normal bowel habits and between patients with diarrhea and with normal bowel habits were 12.4 and 11.2, respectively. These values decreased to 4.4 and 3.3, respectively, when FICE setting 1 images were evaluated. Patients with constipation and diarrhea had significantly brighter (34.4 versus 27.6, P < .0001) and darker (19.6 versus 27.6, P < .0001) SBWC lightness, respectively, than patients with normal bowel habits. The FICE setting 1 images did not reveal significant differences in SBWC lightness between those with constipation and with normal bowel habits (44.1 versus 43.5, P = .83) or between those with diarrhea and with normal bowel habits (39.1 versus 43.5, P = .20). Conclusions : Differences in SBWC color and darkness in the ileum appear to be attributable to bile pigments. Therefore, bile pigments in SBWC may reflect bowel habits.

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

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Amit Kumar Kundu ◽  
Shaikh Anowarul Fattah ◽  
Mamshad Nayeem Rizve
Keyword(s):  
Capsule Endoscopy ◽  
Color Space ◽  
Intensity Variation ◽  
Human Perception ◽  
Wireless Capsule Endoscopy ◽  
Morphological Operations ◽  
Detection Scheme ◽  
Bleeding Detection ◽  
Rgb Color Space ◽  
Wireless Capsule

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%.

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

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Chengliang Wang ◽  
Zhuo Luo ◽  
Xiaoqi Liu ◽  
Jianying Bai ◽  
Guobin Liao
Keyword(s):  
Visual Perception ◽  
Capsule Endoscopy ◽  
Color Space ◽  
Wireless Capsule Endoscopy ◽  
Support Vector ◽  
Svm Classifier ◽  
Phase Congruency ◽  
Region Detection ◽  
Wireless Capsule ◽  
Color Texture

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.

Bleeding Detection in Wireless Capsule Endoscopy Using Color Similarity Coefficient

2012 ◽  
Vol 195-196 ◽  
pp. 307-312 ◽  
Author(s):  
Guo Bing Pan ◽  
Fang Xu ◽  
Jiao Liao Chen
Keyword(s):  
Capsule Endoscopy ◽  
Color Space ◽  
Wireless Capsule Endoscopy ◽  
The Novel ◽  
Similarity Coefficients ◽  
Bleeding Detection ◽  
Color Similarity ◽  
Color Vector ◽  
Wireless Capsule ◽  
Novel Algorithm

Wireless Capsule Endoscopy (WCE) generates a large number of images in one examination of a patient. It is very laborious and time-consuming to detect the WCE video, and limits the wider application of WCE. It is urgent and necessary to develop an automatic and intelligent computer aided bleeding detection technique. This paper proposes the color vector similarity coefficients to measure the color similarity, and based on which, a novel algorithm is implemented to recognize the bleeding in WCE images. The novel algorithm is implemented in RGB color space, and is featured with simple computation and practicability. The experiments show the sensitivity and specificity of this algorithm are 90% and 97% respectively.

scholarly journals Singular Value Decomposition Based Features for Automatic Tumor Detection in Wireless Capsule Endoscopy Images

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Vahid Faghih Dinevari ◽  
Ghader Karimian Khosroshahi ◽  
Mina Zolfy Lighvan
Keyword(s):  
Singular Value Decomposition ◽  
Capsule Endoscopy ◽  
Color Space ◽  
Wireless Capsule Endoscopy ◽  
Singular Value ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Data Set ◽  
Value Decomposition ◽  
Wireless Capsule

Wireless capsule endoscopy (WCE) is a new noninvasive instrument which allows direct observation of the gastrointestinal tract to diagnose its relative diseases. Because of the large number of images obtained from the capsule endoscopy per patient, doctors need too much time to investigate all of them. So, it would be worthwhile to design a system for detecting diseases automatically. In this paper, a new method is presented for automatic detection of tumors in the WCE images. This method will utilize the advantages of the discrete wavelet transform (DWT) and singular value decomposition (SVD) algorithms to extract features from different color channels of the WCE images. Therefore, the extracted features are invariant to rotation and can describe multiresolution characteristics of the WCE images. In order to classify the WCE images, the support vector machine (SVM) method is applied to a data set which includes 400 normal and 400 tumor WCE images. The experimental results show proper performance of the proposed algorithm for detection and isolation of the tumor images which, in the best way, shows 94%, 93%, and 93.5% of sensitivity, specificity, and accuracy in the RGB color space, respectively.

scholarly journals A Convolutional Neural Network Based Disease Diagnosis in Wireless Capsule Endoscopy Images

2019 ◽  
Vol 9 (1) ◽  
pp. 327-331
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Capsule Endoscopy ◽  
Operating Characteristic ◽  
Color Space ◽  
Disease Diagnosis ◽  
Wireless Capsule Endoscopy ◽  
Classifier Design ◽  
Multiple Abnormalities ◽  
Wireless Capsule

In wireless capsule endoscopy (WCE), a swallowable miniature optical endoscope is used to transmit color images of the gastrointestinal tract. However, the number of images transmitted is large, taking a significant amount of the medical expert’s time to review the scan. In this research, we propose a technique to automate the abnormality detection in WCE images. We split the image into several patches and extract features pertaining to each block using a Convolutional neural network (CNN) to increase their generality while overcoming the drawbacks of manually crafted features. We intend to exploit the importance of color information for the task. Experiments are performed to determine the optimal color space components for feature extraction and classifier design. We obtained an area under receiver-operating-characteristic (ROC) curve of approximately 0.8 on a dataset containing multiple abnormalities

Capsule Endoscopy Called Safe, Clinically Useful

2006 ◽  
Vol 40 (12) ◽  
pp. 49
Author(s):  
DAMIAN MCNAMARA
Keyword(s):  
Capsule Endoscopy
Sign in / Sign up

Export Citation Format

Share Document