Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network

This paper investigates the performance of a Deep Convolutional Neural Network (DCNN) algorithm to identify bleeding areas of wireless capsule endoscopy (WCE) images without known prior knowledge of bleeding and normal features of the images. In this study, a pre-processing technique has been propos...

Full description

Bibliographic Details
Main Authors: Rosdiana, Shahril, Saito, Atsushi, Shimizu, Akinobu, Sabariah, Baharun
Format: Article
Language:English
Published: Institute of Information Science 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/26711/1/Bleeding%20classification%20of%20enhanced%20wireless%20capsule%20endoscopy%20images%20.pdf
_version_ 1825813029471649792
author Rosdiana, Shahril
Saito, Atsushi
Shimizu, Akinobu
Sabariah, Baharun
author_facet Rosdiana, Shahril
Saito, Atsushi
Shimizu, Akinobu
Sabariah, Baharun
author_sort Rosdiana, Shahril
collection UMP
description This paper investigates the performance of a Deep Convolutional Neural Network (DCNN) algorithm to identify bleeding areas of wireless capsule endoscopy (WCE) images without known prior knowledge of bleeding and normal features of the images. In this study, a pre-processing technique has been proposed to improve the classification accuracy of WCE images into bleeding areas and normal areas by enhancing the WCE images. The proposed technique is applied to WCE images from six cases and divided into one training case and five test cases. To evaluate the effectiveness of the processes, the results were then compared between DCNN, SVM and Fuzzy, and also between DCNN with completely enhanced images and DCNN with normalized images. DCNN has shown to give a better result compared to SVM and Fuzzy logic; and the latter experiment has shown that the WCE images that have undergone the proposed enhancement technique gives better classification result compared to those images that did not go through the technique. The specificity, sensitivity and average are 0.8703, 0.8271 and 0.8907 respectively. In conclusion, DCNN has been proven to be able to successfully detecting bleeding areas from images without having any specific knowledge on imaging diagnosis or pathology.
first_indexed 2024-03-06T12:37:57Z
format Article
id UMPir26711
institution Universiti Malaysia Pahang
language English
last_indexed 2024-03-06T12:37:57Z
publishDate 2020
publisher Institute of Information Science
record_format dspace
spelling UMPir267112020-03-12T06:19:46Z http://umpir.ump.edu.my/id/eprint/26711/ Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network Rosdiana, Shahril Saito, Atsushi Shimizu, Akinobu Sabariah, Baharun QA76 Computer software This paper investigates the performance of a Deep Convolutional Neural Network (DCNN) algorithm to identify bleeding areas of wireless capsule endoscopy (WCE) images without known prior knowledge of bleeding and normal features of the images. In this study, a pre-processing technique has been proposed to improve the classification accuracy of WCE images into bleeding areas and normal areas by enhancing the WCE images. The proposed technique is applied to WCE images from six cases and divided into one training case and five test cases. To evaluate the effectiveness of the processes, the results were then compared between DCNN, SVM and Fuzzy, and also between DCNN with completely enhanced images and DCNN with normalized images. DCNN has shown to give a better result compared to SVM and Fuzzy logic; and the latter experiment has shown that the WCE images that have undergone the proposed enhancement technique gives better classification result compared to those images that did not go through the technique. The specificity, sensitivity and average are 0.8703, 0.8271 and 0.8907 respectively. In conclusion, DCNN has been proven to be able to successfully detecting bleeding areas from images without having any specific knowledge on imaging diagnosis or pathology. Institute of Information Science 2020 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/26711/1/Bleeding%20classification%20of%20enhanced%20wireless%20capsule%20endoscopy%20images%20.pdf Rosdiana, Shahril and Saito, Atsushi and Shimizu, Akinobu and Sabariah, Baharun (2020) Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network. Journal of Information Science and Engineering, 36 (1). pp. 91-108. ISSN 1016-2364. (Published) http://jise.iis.sinica.edu.tw/JISESearch/pages/View/PaperView.jsf?keyId=172_2294
spellingShingle QA76 Computer software
Rosdiana, Shahril
Saito, Atsushi
Shimizu, Akinobu
Sabariah, Baharun
Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title_full Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title_fullStr Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title_full_unstemmed Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title_short Bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
title_sort bleeding classification of enhanced wireless capsule endoscopy images using deep convolutional neural network
topic QA76 Computer software
url http://umpir.ump.edu.my/id/eprint/26711/1/Bleeding%20classification%20of%20enhanced%20wireless%20capsule%20endoscopy%20images%20.pdf
work_keys_str_mv AT rosdianashahril bleedingclassificationofenhancedwirelesscapsuleendoscopyimagesusingdeepconvolutionalneuralnetwork
AT saitoatsushi bleedingclassificationofenhancedwirelesscapsuleendoscopyimagesusingdeepconvolutionalneuralnetwork
AT shimizuakinobu bleedingclassificationofenhancedwirelesscapsuleendoscopyimagesusingdeepconvolutionalneuralnetwork
AT sabariahbaharun bleedingclassificationofenhancedwirelesscapsuleendoscopyimagesusingdeepconvolutionalneuralnetwork