Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images
Detection of abnormalities in wireless capsule endoscopy (WCE) images is a challenging task. Typically, these images suffer from low contrast, complex background, variations in lesion shape and color, which affect the accuracy of their segmentation and subsequent classification. This research propos...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/6/1265 |
| _version_ | 1828280115086229504 |
|---|---|
| author | Haya Alaskar Abir Hussain Nourah Al-Aseem Panos Liatsis Dhiya Al-Jumeily |
| author_facet | Haya Alaskar Abir Hussain Nourah Al-Aseem Panos Liatsis Dhiya Al-Jumeily |
| author_sort | Haya Alaskar |
| collection | DOAJ |
| description | Detection of abnormalities in wireless capsule endoscopy (WCE) images is a challenging task. Typically, these images suffer from low contrast, complex background, variations in lesion shape and color, which affect the accuracy of their segmentation and subsequent classification. This research proposes an automated system for detection and classification of ulcers in WCE images, based on state-of-the-art deep learning networks. Deep learning techniques, and in particular, convolutional neural networks (CNNs), have recently become popular in the analysis and recognition of medical images. The medical image datasets used in this study were obtained from WCE video frames. In this work, two milestone CNN architectures, namely the AlexNet and the GoogLeNet are extensively evaluated in object classification into ulcer or non-ulcer. Furthermore, we examine and analyze the images identified as containing ulcer objects to evaluate the efficiency of the utilized CNNs. Extensive experiments show that CNNs deliver superior performance, surpassing traditional machine learning methods by large margins, which supports their effectiveness as automated diagnosis tools. |
| first_indexed | 2024-04-13T07:54:20Z |
| format | Article |
| id | doaj.art-0f92f8bc90054f48a5c54634cf9a9591 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:54:20Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0f92f8bc90054f48a5c54634cf9a95912022-12-22T02:55:26ZengMDPI AGSensors1424-82202019-03-01196126510.3390/s19061265s19061265Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy ImagesHaya Alaskar0Abir Hussain1Nourah Al-Aseem2Panos Liatsis3Dhiya Al-Jumeily4Department of Computer Science, College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi ArabiaDepartment of Computer Science, Liverpool John Moores University, Liverpool L3 3AF, UKDepartment of Computer Science, College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi ArabiaDepartment of Computer Science, Khalifa University of Science and Technology, Abu Dhabi 127788, UAEDepartment of Computer Science, Liverpool John Moores University, Liverpool L3 3AF, UKDetection of abnormalities in wireless capsule endoscopy (WCE) images is a challenging task. Typically, these images suffer from low contrast, complex background, variations in lesion shape and color, which affect the accuracy of their segmentation and subsequent classification. This research proposes an automated system for detection and classification of ulcers in WCE images, based on state-of-the-art deep learning networks. Deep learning techniques, and in particular, convolutional neural networks (CNNs), have recently become popular in the analysis and recognition of medical images. The medical image datasets used in this study were obtained from WCE video frames. In this work, two milestone CNN architectures, namely the AlexNet and the GoogLeNet are extensively evaluated in object classification into ulcer or non-ulcer. Furthermore, we examine and analyze the images identified as containing ulcer objects to evaluate the efficiency of the utilized CNNs. Extensive experiments show that CNNs deliver superior performance, surpassing traditional machine learning methods by large margins, which supports their effectiveness as automated diagnosis tools.http://www.mdpi.com/1424-8220/19/6/1265deep learning networksAlexNetGoogLeNetconvolutional neural networkswireless capsule endoscopyulcer detection |
| spellingShingle | Haya Alaskar Abir Hussain Nourah Al-Aseem Panos Liatsis Dhiya Al-Jumeily Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images Sensors deep learning networks AlexNet GoogLeNet convolutional neural networks wireless capsule endoscopy ulcer detection |
| title | Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images |
| title_full | Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images |
| title_fullStr | Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images |
| title_full_unstemmed | Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images |
| title_short | Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images |
| title_sort | application of convolutional neural networks for automated ulcer detection in wireless capsule endoscopy images |
| topic | deep learning networks AlexNet GoogLeNet convolutional neural networks wireless capsule endoscopy ulcer detection |
| url | http://www.mdpi.com/1424-8220/19/6/1265 |
| work_keys_str_mv | AT hayaalaskar applicationofconvolutionalneuralnetworksforautomatedulcerdetectioninwirelesscapsuleendoscopyimages AT abirhussain applicationofconvolutionalneuralnetworksforautomatedulcerdetectioninwirelesscapsuleendoscopyimages AT nourahalaseem applicationofconvolutionalneuralnetworksforautomatedulcerdetectioninwirelesscapsuleendoscopyimages AT panosliatsis applicationofconvolutionalneuralnetworksforautomatedulcerdetectioninwirelesscapsuleendoscopyimages AT dhiyaaljumeily applicationofconvolutionalneuralnetworksforautomatedulcerdetectioninwirelesscapsuleendoscopyimages |