Small intestine bleeding detection using color threshold and morphological operation in WCE images

Citation

Al Mamun, Abdullah Sarwar and Hossain, M. S. and Em, Poh Ping and Tahabilder, Anik and Sultana, R. and Islam, M. A. (2021) Small intestine bleeding detection using color threshold and morphological operation in WCE images. International Journal of Electrical and Computer Engineering (IJECE), 11 (4). p. 3040. ISSN 2088-8708

[img] Text
Small intestine bleeding detection using color threshold....pdf
Restricted to Repository staff only

Download (831kB)

Abstract

Wireless capsule endoscopy (WCE) is a significant modern technique for observing the whole gastroenterological tract to diagnose various diseases like bleeding, ulcer, tumor, Crohn's disease, polyps etc in a non-invasive manner. However, it will make a substantial onus for physicians like human oversight errors with time consumption for manual checking of a vast amount of image frames. These problems motivate the researchers to employ a computer-aided system to classify the particular information from the image frames. Therefore, a computer-aided system based on the color threshold and morphological operation has been proposed in this research to recognize specified bleeding images from the WCE. Besides, A unique classifier, quadratic support vector machine (QSVM) has been employed for classifying the bleeding and non-bleeding images with the statistical feature vector in HSV color space. After extensive experiments on clinical data, 95.8% accuracy, 95% sensitivity, 97% specificity, 80% precision, 99% negative predicted value and 85% F1 score has been achieved, which outperforms some of the existing methods in this regard. It is expected that this methodology would bring a significant contribution to the WCE technology.

Item Type: Article
Uncontrolled Keywords: Capsule endoscopy
Subjects: R Medicine > RC Internal medicine > RC71-78.7 Examination. Diagnosis
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 01 Jul 2021 01:42
Last Modified: 01 Jul 2021 01:42
URII: http://shdl.mmu.edu.my/id/eprint/8790

Downloads

Downloads per month over past year

View ItemEdit (login required)