DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy
Wireless Capsule Endoscopy (WCE) is a noninvasive diagnostic technique enabling the inspection of the whole gastrointestinal (GI) tract by capturing and wirelessly transmitting thousands of color images. Proprietary software “stitches” the images into videos for examination by accredited readers. Ho...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Computational and Mathematical Methods in Medicine |
Online Access: | http://dx.doi.org/10.1155/2018/2026962 |
id |
doaj-7cc280942f9542e6b07f42930da2b4d0 |
---|---|
record_format |
Article |
spelling |
doaj-7cc280942f9542e6b07f42930da2b4d02020-11-25T01:40:29ZengHindawi LimitedComputational and Mathematical Methods in Medicine1748-670X1748-67182018-01-01201810.1155/2018/20269622026962DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule EndoscopyMichael D. Vasilakakis0Dimitris K. Iakovidis1Evaggelos Spyrou2Anastasios Koulaouzidis3Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceDepartment of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceDepartment of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceEndoscopy Unit, The Royal Infirmary of Edinburgh, Edinburgh, UKWireless Capsule Endoscopy (WCE) is a noninvasive diagnostic technique enabling the inspection of the whole gastrointestinal (GI) tract by capturing and wirelessly transmitting thousands of color images. Proprietary software “stitches” the images into videos for examination by accredited readers. However, the videos produced are of large length and consequently the reading task becomes harder and more prone to human errors. Automating the WCE reading process could contribute in both the reduction of the examination time and the improvement of its diagnostic accuracy. In this paper, we present a novel feature extraction methodology for automated WCE image analysis. It aims at discriminating various kinds of abnormalities from the normal contents of WCE images, in a machine learning-based classification framework. The extraction of the proposed features involves an unsupervised color-based saliency detection scheme which, unlike current approaches, combines both point and region-level saliency information and the estimation of local and global image color descriptors. The salient point detection process involves estimation of DIstaNces On Selective Aggregation of chRomatic image Components (DINOSARC). The descriptors are extracted from superpixels by coevaluating both point and region-level information. The main conclusions of the experiments performed on a publicly available dataset of WCE images are (a) the proposed salient point detection scheme results in significantly less and more relevant salient points; (b) the proposed descriptors are more discriminative than relevant state-of-the-art descriptors, promising a wider adoption of the proposed approach for computer-aided diagnosis in WCE.http://dx.doi.org/10.1155/2018/2026962 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Michael D. Vasilakakis Dimitris K. Iakovidis Evaggelos Spyrou Anastasios Koulaouzidis |
spellingShingle |
Michael D. Vasilakakis Dimitris K. Iakovidis Evaggelos Spyrou Anastasios Koulaouzidis DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy Computational and Mathematical Methods in Medicine |
author_facet |
Michael D. Vasilakakis Dimitris K. Iakovidis Evaggelos Spyrou Anastasios Koulaouzidis |
author_sort |
Michael D. Vasilakakis |
title |
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy |
title_short |
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy |
title_full |
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy |
title_fullStr |
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy |
title_full_unstemmed |
DINOSARC: Color Features Based on Selective Aggregation of Chromatic Image Components for Wireless Capsule Endoscopy |
title_sort |
dinosarc: color features based on selective aggregation of chromatic image components for wireless capsule endoscopy |
publisher |
Hindawi Limited |
series |
Computational and Mathematical Methods in Medicine |
issn |
1748-670X 1748-6718 |
publishDate |
2018-01-01 |
description |
Wireless Capsule Endoscopy (WCE) is a noninvasive diagnostic technique enabling the inspection of the whole gastrointestinal (GI) tract by capturing and wirelessly transmitting thousands of color images. Proprietary software “stitches” the images into videos for examination by accredited readers. However, the videos produced are of large length and consequently the reading task becomes harder and more prone to human errors. Automating the WCE reading process could contribute in both the reduction of the examination time and the improvement of its diagnostic accuracy. In this paper, we present a novel feature extraction methodology for automated WCE image analysis. It aims at discriminating various kinds of abnormalities from the normal contents of WCE images, in a machine learning-based classification framework. The extraction of the proposed features involves an unsupervised color-based saliency detection scheme which, unlike current approaches, combines both point and region-level saliency information and the estimation of local and global image color descriptors. The salient point detection process involves estimation of DIstaNces On Selective Aggregation of chRomatic image Components (DINOSARC). The descriptors are extracted from superpixels by coevaluating both point and region-level information. The main conclusions of the experiments performed on a publicly available dataset of WCE images are (a) the proposed salient point detection scheme results in significantly less and more relevant salient points; (b) the proposed descriptors are more discriminative than relevant state-of-the-art descriptors, promising a wider adoption of the proposed approach for computer-aided diagnosis in WCE. |
url |
http://dx.doi.org/10.1155/2018/2026962 |
work_keys_str_mv |
AT michaeldvasilakakis dinosarccolorfeaturesbasedonselectiveaggregationofchromaticimagecomponentsforwirelesscapsuleendoscopy AT dimitriskiakovidis dinosarccolorfeaturesbasedonselectiveaggregationofchromaticimagecomponentsforwirelesscapsuleendoscopy AT evaggelosspyrou dinosarccolorfeaturesbasedonselectiveaggregationofchromaticimagecomponentsforwirelesscapsuleendoscopy AT anastasioskoulaouzidis dinosarccolorfeaturesbasedonselectiveaggregationofchromaticimagecomponentsforwirelesscapsuleendoscopy |
_version_ |
1725045464994152448 |